diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..3792896f2dd17641f2a6c602874d01713a5310e9 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +papers/ARCHCODE:[[:space:]]Incorporating[[:space:]]Software[[:space:]]Requirements[[:space:]]in[[:space:]]Code[[:space:]]Generation[[:space:]]with[[:space:]]Large[[:space:]]Language[[:space:]]Models.pdf filter=lfs diff=lfs merge=lfs -text +papers/AST-T5:[[:space:]]Structure-Aware[[:space:]]Pretraining[[:space:]]for[[:space:]]Code[[:space:]]Generation[[:space:]]and[[:space:]]Understanding.pdf filter=lfs diff=lfs merge=lfs -text +papers/CODE4STRUCT:[[:space:]]Code[[:space:]]Generation[[:space:]]for[[:space:]]Few-Shot[[:space:]]Event[[:space:]]Structure[[:space:]]Prediction.pdf filter=lfs diff=lfs merge=lfs -text +papers/CodeBERT:[[:space:]]A[[:space:]]Pre-Trained[[:space:]]Model[[:space:]]for[[:space:]]Programming[[:space:]]and[[:space:]]Natural[[:space:]]Languages.pdf filter=lfs diff=lfs merge=lfs -text +papers/CodeGeeX:[[:space:]]A[[:space:]]Pre-Trained[[:space:]]Model[[:space:]]for[[:space:]]Code[[:space:]]Generation[[:space:]]with[[:space:]]Multilingual[[:space:]]Benchmarking[[:space:]]on[[:space:]]HumanEval-X.pdf filter=lfs diff=lfs merge=lfs -text +papers/CodeGemma[[:space:]]Open[[:space:]]Code[[:space:]]Models[[:space:]][[:space:]]Based[[:space:]]on[[:space:]]Gemma.pdf filter=lfs diff=lfs merge=lfs -text +papers/CodeT5+:[[:space:]]Open[[:space:]]Code[[:space:]]Large[[:space:]]Language[[:space:]]Models[[:space:]]for[[:space:]]Code[[:space:]]Understanding[[:space:]]and[[:space:]]Generation.pdf filter=lfs diff=lfs merge=lfs -text +papers/CoTexT:[[:space:]]Multi-task[[:space:]]Learning[[:space:]]with[[:space:]]Code-Text[[:space:]]Transformer.pdf filter=lfs diff=lfs merge=lfs -text +papers/Evaluating[[:space:]]the[[:space:]]Code[[:space:]]Quality[[:space:]]of[[:space:]]AI-Assisted[[:space:]]Code[[:space:]]Generation[[:space:]]Tools:[[:space:]]An[[:space:]]Empirical[[:space:]]Study[[:space:]]on[[:space:]]GitHub[[:space:]]Copilot,[[:space:]]Amazon[[:space:]]CodeWhisperer,[[:space:]]and[[:space:]]ChatGPT.pdf filter=lfs diff=lfs merge=lfs -text +papers/GRAPH[[:space:]]CODE[[:space:]]BERT:[[:space:]]PRE-TRAINING[[:space:]]CODE[[:space:]]REPRESEN-TATIONS[[:space:]]WITH[[:space:]]DATA[[:space:]]F[[:space:]]LOW.pdf filter=lfs diff=lfs merge=lfs -text +papers/StructCoder_[[:space:]]Structure-Aware[[:space:]]Transformer[[:space:]]for[[:space:]]Code[[:space:]]Generation[[:space:]]-[[:space:]]2206.05239v3.pdf filter=lfs diff=lfs merge=lfs -text +papers/TreeGen:[[:space:]]A[[:space:]]Tree-Based[[:space:]]Transformer[[:space:]]Architecture[[:space:]]for[[:space:]]Code[[:space:]]Generation.pdf filter=lfs diff=lfs merge=lfs -text diff --git a/data/code_corpus.txt b/data/code_corpus.txt new file mode 100644 index 0000000000000000000000000000000000000000..c5dc9da4162f40043d10537541638c2c6273a811 --- /dev/null +++ b/data/code_corpus.txt @@ -0,0 +1,3 @@ +def add(a, b): return a + b +print("Hello, world!") +class HelloWorld: pass diff --git a/data/train.jsonl b/data/train.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9ddefee51231773c5a31552f8482312fccb73938 --- /dev/null +++ b/data/train.jsonl @@ -0,0 +1,2 @@ +{"input": "def add(a, b):", "output": "Returns the sum of a and b."} +{"input": "class Hello:", "output": "A simple Hello class."} diff --git a/environment.yml b/environment.yml new file mode 100644 index 0000000000000000000000000000000000000000..812f9a626b3c0dea33229af3d7ca9295f3b822db --- /dev/null +++ b/environment.yml @@ -0,0 +1,36 @@ +name: myenv +channels: + - defaults + - conda-forge +dependencies: + - python=3.10 + - transformers + - datasets + - sentencepiece + - langchain + - networkx + - evaluate + - matplotlib + - seaborn + - lark + - fastapi + - uvicorn + - jupyterlab + - ipykernel + - tqdm + - scikit-learn + - pandas + - numpy + - pytorch + - pip + - pip: + - ollama + - rouge-score + - huggingface_hub + - accelerate + - peft + - bitsandbytes + - einops + - safetensors + - wandb + diff --git a/minicoderx-model/checkpoint-2/config.json b/minicoderx-model/checkpoint-2/config.json new file mode 100644 index 0000000000000000000000000000000000000000..875ba5d9d44b85d53592976d4c2b6425bc63516f --- /dev/null +++ b/minicoderx-model/checkpoint-2/config.json @@ -0,0 +1,61 @@ +{ + "_name_or_path": "t5-small", + "architectures": [ + "T5ForConditionalGeneration" + ], + "classifier_dropout": 0.0, + "d_ff": 2048, + "d_kv": 64, + "d_model": 512, + "decoder_start_token_id": 0, + "dense_act_fn": "relu", + "dropout_rate": 0.1, + "eos_token_id": 1, + "feed_forward_proj": "relu", + "initializer_factor": 1.0, + "is_encoder_decoder": true, + "is_gated_act": false, + "layer_norm_epsilon": 1e-06, + "model_type": "t5", + "n_positions": 512, + "num_decoder_layers": 6, + "num_heads": 8, + "num_layers": 6, + "output_past": true, + "pad_token_id": 0, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "task_specific_params": { + "summarization": { + "early_stopping": true, + "length_penalty": 2.0, + "max_length": 200, + "min_length": 30, + "no_repeat_ngram_size": 3, + "num_beams": 4, + "prefix": "summarize: " + }, + "translation_en_to_de": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to German: " + }, + "translation_en_to_fr": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to French: " + }, + "translation_en_to_ro": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to Romanian: " + } + }, + "torch_dtype": "float32", + "transformers_version": "4.49.0", + "use_cache": true, + "vocab_size": 32128 +} diff --git a/minicoderx-model/checkpoint-2/generation_config.json b/minicoderx-model/checkpoint-2/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..eba25c5db1745fe5324f4f7e8890c19853e21453 --- /dev/null +++ b/minicoderx-model/checkpoint-2/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "decoder_start_token_id": 0, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.49.0" +} diff --git a/minicoderx-model/checkpoint-2/model.safetensors b/minicoderx-model/checkpoint-2/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73b0c80b0ab4011ccb8a925990d79d719418e2b9 --- /dev/null +++ b/minicoderx-model/checkpoint-2/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05315572729341ea7678bacfca08ae712b079e2f0f709ea828850bb2fde1b75e +size 242041896 diff --git a/minicoderx-model/checkpoint-2/optimizer.pt b/minicoderx-model/checkpoint-2/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..555ea014a2ee85a5df7c69536c9155f7c2cf2130 --- /dev/null +++ b/minicoderx-model/checkpoint-2/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294cd1bddba987df78f346e471aeb9ee05979de08064749d4a94fb8e5bc366da +size 484159866 diff --git a/minicoderx-model/checkpoint-2/rng_state.pth b/minicoderx-model/checkpoint-2/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..fb40f18859bf53c2201e15949e65c50b0ab37a66 --- /dev/null +++ b/minicoderx-model/checkpoint-2/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1565ec4ad382943310a6a711595e3c8d4aed2df4b2b87d014ae460d26b0d6aa +size 13990 diff --git a/minicoderx-model/checkpoint-2/scheduler.pt b/minicoderx-model/checkpoint-2/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6071eca089aaebae297215d26be25de736e09a63 --- /dev/null +++ b/minicoderx-model/checkpoint-2/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27ddd0715a8a938994a234170508c4e373cb0cfabcdcd5c8c55491154f6015a +size 1064 diff --git a/minicoderx-model/checkpoint-2/special_tokens_map.json b/minicoderx-model/checkpoint-2/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..c4f3a23212f68c057831f004b6a4e51f74659e28 --- /dev/null +++ b/minicoderx-model/checkpoint-2/special_tokens_map.json @@ -0,0 +1,140 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "cls_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "sep_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/minicoderx-model/checkpoint-2/tokenizer.json b/minicoderx-model/checkpoint-2/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c8603d605f34cbb63aabdb84d1bad9812c7cd313 --- /dev/null +++ b/minicoderx-model/checkpoint-2/tokenizer.json @@ -0,0 +1,1263 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 128, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 128 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "" + }, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 4, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 60, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 61, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 62, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 63, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 64, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 65, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 66, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 67, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 68, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 69, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 70, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 71, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 72, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 73, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 74, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 75, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 76, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 77, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 78, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 79, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 80, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 81, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 82, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 83, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 84, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 85, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 86, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 87, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 88, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 89, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 90, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 91, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 92, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 93, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 94, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 95, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 96, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 97, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 98, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 99, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 100, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 101, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 102, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 103, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 104, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 105, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 106, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 107, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 108, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 109, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 110, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 111, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 112, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 113, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 114, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 115, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 116, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 117, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 118, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 119, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 120, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 121, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 122, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 123, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 124, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 125, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 126, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 127, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 128, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 129, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 130, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 131, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 132, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 133, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 134, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 135, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 136, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 137, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 138, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 139, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 140, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 141, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 142, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 143, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 144, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 145, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 146, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 147, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 148, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 149, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 150, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 151, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 152, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 153, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 154, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 155, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 156, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 157, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 158, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 159, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Sequence", + "normalizers": [ + { + "type": "NFD" + }, + { + "type": "Lowercase" + }, + { + "type": "StripAccents" + } + ] + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": { + "type": "TemplateProcessing", + "single": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "pair": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "B", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "special_tokens": { + "": { + "id": "", + "ids": [ + 2 + ], + "tokens": [ + "" + ] + }, + "": { + "id": "", + "ids": [ + 1 + ], + "tokens": [ + "" + ] + } + } + }, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": null, + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "ignore_merges": false, + "vocab": { + "": 0, + "": 1, + "": 2, + "": 3, + "": 4, + "!": 5, + "\"": 6, + "(": 7, + ")": 8, + "+": 9, + ",": 10, + ":": 11, + "a": 12, + "b": 13, + "c": 14, + "d": 15, + "e": 16, + "f": 17, + "h": 18, + "i": 19, + "l": 20, + "n": 21, + "o": 22, + "p": 23, + "r": 24, + "s": 25, + "t": 26, + "u": 27, + "w": 28, + "as": 29, + "el": 30, + "hel": 31, + "ld": 32, + "lo": 33, + "or": 34, + "wor": 35, + "ass": 36, + "hello": 37, + "world": 38, + "!\"": 39, + "(\"": 40, + "):": 41, + "ad": 42, + "cl": 43, + "de": 44, + "et": 45, + "in": 46, + "pr": 47, + "pass": 48, + "rn": 49, + "ret": 50, + "urn": 51, + "helloworld": 52, + "!\")": 53, + "add": 54, + "class": 55, + "def": 56, + "int": 57, + "print": 58, + "return": 59 + }, + "merges": [ + [ + "a", + "s" + ], + [ + "e", + "l" + ], + [ + "h", + "el" + ], + [ + "l", + "d" + ], + [ + "l", + "o" + ], + [ + "o", + "r" + ], + [ + "w", + "or" + ], + [ + "as", + "s" + ], + [ + "hel", + "lo" + ], + [ + "wor", + "ld" + ], + [ + "!", + "\"" + ], + [ + "(", + "\"" + ], + [ + ")", + ":" + ], + [ + "a", + "d" + ], + [ + "c", + "l" + ], + [ + "d", + "e" + ], + [ + "e", + "t" + ], + [ + "i", + "n" + ], + [ + "p", + "r" + ], + [ + "p", + "ass" + ], + [ + "r", + "n" + ], + [ + "r", + "et" + ], + [ + "u", + "rn" + ], + [ + "hello", + "world" + ], + [ + "!\"", + ")" + ], + [ + "ad", + "d" + ], + [ + "cl", + "ass" + ], + [ + "de", + "f" + ], + [ + "in", + "t" + ], + [ + "pr", + "int" + ], + [ + "ret", + "urn" + ] + ] + } +} \ No newline at end of file diff --git a/minicoderx-model/checkpoint-2/tokenizer_config.json b/minicoderx-model/checkpoint-2/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3a220e400d438fc849e6afa79b01bf62c91cc423 --- /dev/null +++ b/minicoderx-model/checkpoint-2/tokenizer_config.json @@ -0,0 +1,958 @@ +{ + "add_prefix_space": null, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "109": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "110": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "127": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "129": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "130": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "131": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "132": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "133": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "134": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "135": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "136": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "137": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "138": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "139": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "140": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "141": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "142": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "143": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "144": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "145": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "146": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "147": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "148": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "149": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "150": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "153": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "155": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "156": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "157": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "158": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "159": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "cls_token": "", + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "tokenizer_class": "T5TokenizerFast", + "unk_token": "" +} diff --git a/minicoderx-model/checkpoint-2/trainer_state.json b/minicoderx-model/checkpoint-2/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..523fda659c33662693ea196540f67fb766d42110 --- /dev/null +++ b/minicoderx-model/checkpoint-2/trainer_state.json @@ -0,0 +1,32 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 2, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [], + "logging_steps": 10, + "max_steps": 3, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 135341801472.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/minicoderx-model/checkpoint-2/training_args.bin b/minicoderx-model/checkpoint-2/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94f0f9dcfb56305e207b45a6ae9d8a6dadd5532 --- /dev/null +++ b/minicoderx-model/checkpoint-2/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd544df3e986cab3c0663ced7b6b3ca6903b0db2be881d69b5180d0077410a13 +size 5304 diff --git a/minicoderx-model/checkpoint-3/config.json b/minicoderx-model/checkpoint-3/config.json new file mode 100644 index 0000000000000000000000000000000000000000..875ba5d9d44b85d53592976d4c2b6425bc63516f --- /dev/null +++ b/minicoderx-model/checkpoint-3/config.json @@ -0,0 +1,61 @@ +{ + "_name_or_path": "t5-small", + "architectures": [ + "T5ForConditionalGeneration" + ], + "classifier_dropout": 0.0, + "d_ff": 2048, + "d_kv": 64, + "d_model": 512, + "decoder_start_token_id": 0, + "dense_act_fn": "relu", + "dropout_rate": 0.1, + "eos_token_id": 1, + "feed_forward_proj": "relu", + "initializer_factor": 1.0, + "is_encoder_decoder": true, + "is_gated_act": false, + "layer_norm_epsilon": 1e-06, + "model_type": "t5", + "n_positions": 512, + "num_decoder_layers": 6, + "num_heads": 8, + "num_layers": 6, + "output_past": true, + "pad_token_id": 0, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "task_specific_params": { + "summarization": { + "early_stopping": true, + "length_penalty": 2.0, + "max_length": 200, + "min_length": 30, + "no_repeat_ngram_size": 3, + "num_beams": 4, + "prefix": "summarize: " + }, + "translation_en_to_de": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to German: " + }, + "translation_en_to_fr": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to French: " + }, + "translation_en_to_ro": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to Romanian: " + } + }, + "torch_dtype": "float32", + "transformers_version": "4.49.0", + "use_cache": true, + "vocab_size": 32128 +} diff --git a/minicoderx-model/checkpoint-3/generation_config.json b/minicoderx-model/checkpoint-3/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..eba25c5db1745fe5324f4f7e8890c19853e21453 --- /dev/null +++ b/minicoderx-model/checkpoint-3/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "decoder_start_token_id": 0, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.49.0" +} diff --git a/minicoderx-model/checkpoint-3/model.safetensors b/minicoderx-model/checkpoint-3/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b71e841b08bb0bb7c7bcec135ed79c0f57125953 --- /dev/null +++ b/minicoderx-model/checkpoint-3/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58f23c7336fdae923aa51a04dcc36156d74b7fd8d1a336b6c9f62f80b899e69 +size 242041896 diff --git a/minicoderx-model/checkpoint-3/optimizer.pt b/minicoderx-model/checkpoint-3/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0eebde83f44c64c233f69b81cdefec9bca2c5db --- /dev/null +++ b/minicoderx-model/checkpoint-3/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2eb64c382fe83bd68b60ad8ec5356bbffb6f14c5bda4dddda53f669be44474e +size 484159866 diff --git a/minicoderx-model/checkpoint-3/rng_state.pth b/minicoderx-model/checkpoint-3/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e4e9f742f3056ee4252b829618a3e3870e04e95 --- /dev/null +++ b/minicoderx-model/checkpoint-3/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337d385b937fddd772e2cc2209cc85d048e2e3ef39019b832d2ab98922f62043 +size 13990 diff --git a/minicoderx-model/checkpoint-3/scheduler.pt b/minicoderx-model/checkpoint-3/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dddcd627c7d6ce0e47edce73f1b9d33f810b141 --- /dev/null +++ b/minicoderx-model/checkpoint-3/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a41b254d981983d12a5d0bed17f4768863ab9648e2daeb9b71c409365e3b73 +size 1064 diff --git a/minicoderx-model/checkpoint-3/special_tokens_map.json b/minicoderx-model/checkpoint-3/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..c4f3a23212f68c057831f004b6a4e51f74659e28 --- /dev/null +++ b/minicoderx-model/checkpoint-3/special_tokens_map.json @@ -0,0 +1,140 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "cls_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "sep_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/minicoderx-model/checkpoint-3/tokenizer.json b/minicoderx-model/checkpoint-3/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c8603d605f34cbb63aabdb84d1bad9812c7cd313 --- /dev/null +++ b/minicoderx-model/checkpoint-3/tokenizer.json @@ -0,0 +1,1263 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 128, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 128 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "" + }, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 4, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 60, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 61, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 62, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 63, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 64, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 65, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 66, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 67, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 68, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 69, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 70, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 71, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 72, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 73, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 74, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 75, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 76, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 77, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 78, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 79, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 80, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 81, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 82, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 83, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 84, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 85, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 86, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 87, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 88, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 89, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 90, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 91, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 92, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 93, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 94, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 95, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 96, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 97, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 98, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 99, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 100, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 101, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 102, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 103, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 104, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 105, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 106, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 107, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 108, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 109, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 110, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 111, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 112, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 113, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 114, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 115, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 116, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 117, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 118, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 119, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 120, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 121, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 122, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 123, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 124, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 125, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 126, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 127, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 128, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 129, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 130, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 131, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 132, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 133, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 134, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 135, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 136, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 137, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 138, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 139, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 140, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 141, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 142, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 143, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 144, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 145, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 146, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 147, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 148, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 149, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 150, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 151, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 152, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 153, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 154, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 155, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 156, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 157, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 158, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 159, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Sequence", + "normalizers": [ + { + "type": "NFD" + }, + { + "type": "Lowercase" + }, + { + "type": "StripAccents" + } + ] + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": { + "type": "TemplateProcessing", + "single": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "pair": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "B", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "special_tokens": { + "": { + "id": "", + "ids": [ + 2 + ], + "tokens": [ + "" + ] + }, + "": { + "id": "", + "ids": [ + 1 + ], + "tokens": [ + "" + ] + } + } + }, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": null, + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "ignore_merges": false, + "vocab": { + "": 0, + "": 1, + "": 2, + "": 3, + "": 4, + "!": 5, + "\"": 6, + "(": 7, + ")": 8, + "+": 9, + ",": 10, + ":": 11, + "a": 12, + "b": 13, + "c": 14, + "d": 15, + "e": 16, + "f": 17, + "h": 18, + "i": 19, + "l": 20, + "n": 21, + "o": 22, + "p": 23, + "r": 24, + "s": 25, + "t": 26, + "u": 27, + "w": 28, + "as": 29, + "el": 30, + "hel": 31, + "ld": 32, + "lo": 33, + "or": 34, + "wor": 35, + "ass": 36, + "hello": 37, + "world": 38, + "!\"": 39, + "(\"": 40, + "):": 41, + "ad": 42, + "cl": 43, + "de": 44, + "et": 45, + "in": 46, + "pr": 47, + "pass": 48, + "rn": 49, + "ret": 50, + "urn": 51, + "helloworld": 52, + "!\")": 53, + "add": 54, + "class": 55, + "def": 56, + "int": 57, + "print": 58, + "return": 59 + }, + "merges": [ + [ + "a", + "s" + ], + [ + "e", + "l" + ], + [ + "h", + "el" + ], + [ + "l", + "d" + ], + [ + "l", + "o" + ], + [ + "o", + "r" + ], + [ + "w", + "or" + ], + [ + "as", + "s" + ], + [ + "hel", + "lo" + ], + [ + "wor", + "ld" + ], + [ + "!", + "\"" + ], + [ + "(", + "\"" + ], + [ + ")", + ":" + ], + [ + "a", + "d" + ], + [ + "c", + "l" + ], + [ + "d", + "e" + ], + [ + "e", + "t" + ], + [ + "i", + "n" + ], + [ + "p", + "r" + ], + [ + "p", + "ass" + ], + [ + "r", + "n" + ], + [ + "r", + "et" + ], + [ + "u", + "rn" + ], + [ + "hello", + "world" + ], + [ + "!\"", + ")" + ], + [ + "ad", + "d" + ], + [ + "cl", + "ass" + ], + [ + "de", + "f" + ], + [ + "in", + "t" + ], + [ + "pr", + "int" + ], + [ + "ret", + "urn" + ] + ] + } +} \ No newline at end of file diff --git a/minicoderx-model/checkpoint-3/tokenizer_config.json b/minicoderx-model/checkpoint-3/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3a220e400d438fc849e6afa79b01bf62c91cc423 --- /dev/null +++ b/minicoderx-model/checkpoint-3/tokenizer_config.json @@ -0,0 +1,958 @@ +{ + "add_prefix_space": null, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "109": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "110": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "127": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "129": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "130": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "131": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "132": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "133": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "134": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "135": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "136": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "137": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "138": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "139": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "140": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "141": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "142": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "143": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "144": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "145": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "146": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "147": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "148": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "149": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "150": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "153": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "155": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "156": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "157": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "158": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "159": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "cls_token": "", + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "tokenizer_class": "T5TokenizerFast", + "unk_token": "" +} diff --git a/minicoderx-model/checkpoint-3/trainer_state.json b/minicoderx-model/checkpoint-3/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9229865d752b490a73a38fdda04da0412ec0d87d --- /dev/null +++ b/minicoderx-model/checkpoint-3/trainer_state.json @@ -0,0 +1,32 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 3, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [], + "logging_steps": 10, + "max_steps": 3, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 203012702208.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/minicoderx-model/checkpoint-3/training_args.bin b/minicoderx-model/checkpoint-3/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94f0f9dcfb56305e207b45a6ae9d8a6dadd5532 --- /dev/null +++ b/minicoderx-model/checkpoint-3/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd544df3e986cab3c0663ced7b6b3ca6903b0db2be881d69b5180d0077410a13 +size 5304 diff --git a/minicoderx-model/config.json b/minicoderx-model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..875ba5d9d44b85d53592976d4c2b6425bc63516f --- /dev/null +++ b/minicoderx-model/config.json @@ -0,0 +1,61 @@ +{ + "_name_or_path": "t5-small", + "architectures": [ + "T5ForConditionalGeneration" + ], + "classifier_dropout": 0.0, + "d_ff": 2048, + "d_kv": 64, + "d_model": 512, + "decoder_start_token_id": 0, + "dense_act_fn": "relu", + "dropout_rate": 0.1, + "eos_token_id": 1, + "feed_forward_proj": "relu", + "initializer_factor": 1.0, + "is_encoder_decoder": true, + "is_gated_act": false, + "layer_norm_epsilon": 1e-06, + "model_type": "t5", + "n_positions": 512, + "num_decoder_layers": 6, + "num_heads": 8, + "num_layers": 6, + "output_past": true, + "pad_token_id": 0, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "task_specific_params": { + "summarization": { + "early_stopping": true, + "length_penalty": 2.0, + "max_length": 200, + "min_length": 30, + "no_repeat_ngram_size": 3, + "num_beams": 4, + "prefix": "summarize: " + }, + "translation_en_to_de": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to German: " + }, + "translation_en_to_fr": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to French: " + }, + "translation_en_to_ro": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to Romanian: " + } + }, + "torch_dtype": "float32", + "transformers_version": "4.49.0", + "use_cache": true, + "vocab_size": 32128 +} diff --git a/minicoderx-model/generation_config.json b/minicoderx-model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..eba25c5db1745fe5324f4f7e8890c19853e21453 --- /dev/null +++ b/minicoderx-model/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "decoder_start_token_id": 0, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.49.0" +} diff --git a/minicoderx-model/model.safetensors b/minicoderx-model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b71e841b08bb0bb7c7bcec135ed79c0f57125953 --- /dev/null +++ b/minicoderx-model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58f23c7336fdae923aa51a04dcc36156d74b7fd8d1a336b6c9f62f80b899e69 +size 242041896 diff --git a/minicoderx-model/special_tokens_map.json b/minicoderx-model/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..c4f3a23212f68c057831f004b6a4e51f74659e28 --- /dev/null +++ b/minicoderx-model/special_tokens_map.json @@ -0,0 +1,140 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "cls_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "sep_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/minicoderx-model/tokenizer.json b/minicoderx-model/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c8603d605f34cbb63aabdb84d1bad9812c7cd313 --- /dev/null +++ b/minicoderx-model/tokenizer.json @@ -0,0 +1,1263 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 128, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 128 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "" + }, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 4, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 60, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 61, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 62, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 63, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 64, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 65, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 66, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 67, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 68, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 69, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 70, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 71, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 72, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 73, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 74, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 75, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 76, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 77, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 78, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 79, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 80, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 81, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 82, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 83, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 84, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 85, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 86, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 87, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 88, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 89, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 90, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 91, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 92, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 93, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 94, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 95, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 96, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 97, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 98, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 99, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 100, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 101, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 102, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 103, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 104, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 105, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 106, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 107, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 108, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 109, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 110, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 111, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 112, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 113, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 114, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 115, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 116, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 117, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 118, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 119, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 120, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 121, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 122, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 123, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 124, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 125, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 126, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 127, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 128, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 129, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 130, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 131, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 132, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 133, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 134, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 135, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 136, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 137, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 138, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 139, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 140, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 141, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 142, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 143, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 144, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 145, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 146, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 147, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 148, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 149, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 150, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 151, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 152, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 153, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 154, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 155, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 156, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 157, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 158, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 159, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Sequence", + "normalizers": [ + { + "type": "NFD" + }, + { + "type": "Lowercase" + }, + { + "type": "StripAccents" + } + ] + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": { + "type": "TemplateProcessing", + "single": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "pair": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "B", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "special_tokens": { + "": { + "id": "", + "ids": [ + 2 + ], + "tokens": [ + "" + ] + }, + "": { + "id": "", + "ids": [ + 1 + ], + "tokens": [ + "" + ] + } + } + }, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": null, + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "ignore_merges": false, + "vocab": { + "": 0, + "": 1, + "": 2, + "": 3, + "": 4, + "!": 5, + "\"": 6, + "(": 7, + ")": 8, + "+": 9, + ",": 10, + ":": 11, + "a": 12, + "b": 13, + "c": 14, + "d": 15, + "e": 16, + "f": 17, + "h": 18, + "i": 19, + "l": 20, + "n": 21, + "o": 22, + "p": 23, + "r": 24, + "s": 25, + "t": 26, + "u": 27, + "w": 28, + "as": 29, + "el": 30, + "hel": 31, + "ld": 32, + "lo": 33, + "or": 34, + "wor": 35, + "ass": 36, + "hello": 37, + "world": 38, + "!\"": 39, + "(\"": 40, + "):": 41, + "ad": 42, + "cl": 43, + "de": 44, + "et": 45, + "in": 46, + "pr": 47, + "pass": 48, + "rn": 49, + "ret": 50, + "urn": 51, + "helloworld": 52, + "!\")": 53, + "add": 54, + "class": 55, + "def": 56, + "int": 57, + "print": 58, + "return": 59 + }, + "merges": [ + [ + "a", + "s" + ], + [ + "e", + "l" + ], + [ + "h", + "el" + ], + [ + "l", + "d" + ], + [ + "l", + "o" + ], + [ + "o", + "r" + ], + [ + "w", + "or" + ], + [ + "as", + "s" + ], + [ + "hel", + "lo" + ], + [ + "wor", + "ld" + ], + [ + "!", + "\"" + ], + [ + "(", + "\"" + ], + [ + ")", + ":" + ], + [ + "a", + "d" + ], + [ + "c", + "l" + ], + [ + "d", + "e" + ], + [ + "e", + "t" + ], + [ + "i", + "n" + ], + [ + "p", + "r" + ], + [ + "p", + "ass" + ], + [ + "r", + "n" + ], + [ + "r", + "et" + ], + [ + "u", + "rn" + ], + [ + "hello", + "world" + ], + [ + "!\"", + ")" + ], + [ + "ad", + "d" + ], + [ + "cl", + "ass" + ], + [ + "de", + "f" + ], + [ + "in", + "t" + ], + [ + "pr", + "int" + ], + [ + "ret", + "urn" + ] + ] + } +} \ No newline at end of file diff --git a/minicoderx-model/tokenizer_config.json b/minicoderx-model/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3a220e400d438fc849e6afa79b01bf62c91cc423 --- /dev/null +++ b/minicoderx-model/tokenizer_config.json @@ -0,0 +1,958 @@ +{ + "add_prefix_space": null, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "109": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "110": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "127": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "129": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "130": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "131": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "132": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "133": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "134": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "135": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "136": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "137": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "138": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "139": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "140": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "141": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "142": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "143": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "144": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "145": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "146": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "147": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "148": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "149": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "150": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "153": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "155": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "156": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "157": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "158": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "159": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "cls_token": "", + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "tokenizer_class": "T5TokenizerFast", + "unk_token": "" +} diff --git a/minicoderx-model/training_args.bin b/minicoderx-model/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94f0f9dcfb56305e207b45a6ae9d8a6dadd5532 --- /dev/null +++ b/minicoderx-model/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd544df3e986cab3c0663ced7b6b3ca6903b0db2be881d69b5180d0077410a13 +size 5304 diff --git a/minicoderx-tokenizer/special_tokens_map.json b/minicoderx-tokenizer/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3cffb0d58205ee9f7a6f820e0236d2e3af55643d --- /dev/null +++ b/minicoderx-tokenizer/special_tokens_map.json @@ -0,0 +1,7 @@ +{ + "cls_token": "", + "mask_token": "", + "pad_token": "", + "sep_token": "", + "unk_token": "" +} diff --git a/minicoderx-tokenizer/tokenizer.json b/minicoderx-tokenizer/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..d61df62bcc1a427718c1b652d068eb05460951e3 --- /dev/null +++ b/minicoderx-tokenizer/tokenizer.json @@ -0,0 +1,349 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 4, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Sequence", + "normalizers": [ + { + "type": "NFD" + }, + { + "type": "Lowercase" + }, + { + "type": "StripAccents" + } + ] + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": { + "type": "TemplateProcessing", + "single": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "pair": [ + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "B", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "special_tokens": { + "": { + "id": "", + "ids": [ + 2 + ], + "tokens": [ + "" + ] + }, + "": { + "id": "", + "ids": [ + 1 + ], + "tokens": [ + "" + ] + } + } + }, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": null, + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "ignore_merges": false, + "vocab": { + "": 0, + "": 1, + "": 2, + "": 3, + "": 4, + "!": 5, + "\"": 6, + "(": 7, + ")": 8, + "+": 9, + ",": 10, + ":": 11, + "a": 12, + "b": 13, + "c": 14, + "d": 15, + "e": 16, + "f": 17, + "h": 18, + "i": 19, + "l": 20, + "n": 21, + "o": 22, + "p": 23, + "r": 24, + "s": 25, + "t": 26, + "u": 27, + "w": 28, + "as": 29, + "el": 30, + "hel": 31, + "ld": 32, + "lo": 33, + "or": 34, + "wor": 35, + "ass": 36, + "hello": 37, + "world": 38, + "!\"": 39, + "(\"": 40, + "):": 41, + "ad": 42, + "cl": 43, + "de": 44, + "et": 45, + "in": 46, + "pr": 47, + "pass": 48, + "rn": 49, + "ret": 50, + "urn": 51, + "helloworld": 52, + "!\")": 53, + "add": 54, + "class": 55, + "def": 56, + "int": 57, + "print": 58, + "return": 59 + }, + "merges": [ + [ + "a", + "s" + ], + [ + "e", + "l" + ], + [ + "h", + "el" + ], + [ + "l", + "d" + ], + [ + "l", + "o" + ], + [ + "o", + "r" + ], + [ + "w", + "or" + ], + [ + "as", + "s" + ], + [ + "hel", + "lo" + ], + [ + "wor", + "ld" + ], + [ + "!", + "\"" + ], + [ + "(", + "\"" + ], + [ + ")", + ":" + ], + [ + "a", + "d" + ], + [ + "c", + "l" + ], + [ + "d", + "e" + ], + [ + "e", + "t" + ], + [ + "i", + "n" + ], + [ + "p", + "r" + ], + [ + "p", + "ass" + ], + [ + "r", + "n" + ], + [ + "r", + "et" + ], + [ + "u", + "rn" + ], + [ + "hello", + "world" + ], + [ + "!\"", + ")" + ], + [ + "ad", + "d" + ], + [ + "cl", + "ass" + ], + [ + "de", + "f" + ], + [ + "in", + "t" + ], + [ + "pr", + "int" + ], + [ + "ret", + "urn" + ] + ] + } +} \ No newline at end of file diff --git a/minicoderx-tokenizer/tokenizer_config.json b/minicoderx-tokenizer/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..00f3b94bd0e1cdf2a9f9b5b59be69b35f725e8ab --- /dev/null +++ b/minicoderx-tokenizer/tokenizer_config.json @@ -0,0 +1,53 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": false, + "cls_token": "", + "extra_special_tokens": {}, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "tokenizer_class": "PreTrainedTokenizer", + "unk_token": "" +} diff --git a/papers/ARCHCODE: Incorporating Software Requirements in Code Generation with Large Language Models.pdf b/papers/ARCHCODE: Incorporating Software Requirements in Code Generation with Large Language Models.pdf new file mode 100644 index 0000000000000000000000000000000000000000..86f22f0030a170f8464b5669940341e44c088b86 --- /dev/null +++ b/papers/ARCHCODE: Incorporating Software Requirements in Code Generation with Large Language Models.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bdccbd0a0269d01381b46634bed78101c788a5545bcaf32e6d4f712654f908e +size 557731 diff --git a/papers/AST-T5: Structure-Aware Pretraining for Code Generation and Understanding.pdf b/papers/AST-T5: Structure-Aware Pretraining for Code Generation and Understanding.pdf new file mode 100644 index 0000000000000000000000000000000000000000..292057fae21fb7ef80c9e59535b931892b60ed82 --- /dev/null +++ b/papers/AST-T5: Structure-Aware Pretraining for Code Generation and Understanding.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44dceedeadc981bc793a882a8bf7b76600ea23d09c923be46295257c296b709e +size 271471 diff --git a/papers/CODE4STRUCT: Code Generation for Few-Shot Event Structure Prediction.pdf b/papers/CODE4STRUCT: Code Generation for Few-Shot Event Structure Prediction.pdf new file mode 100644 index 0000000000000000000000000000000000000000..4942367df3a9180c7776bef08241ad973f41996b --- /dev/null +++ b/papers/CODE4STRUCT: Code Generation for Few-Shot Event Structure Prediction.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d1cec3c94263d77c67845e21be34ae978274eae40e8991416fdac0ff7fed65 +size 675766 diff --git a/papers/CoTexT: Multi-task Learning with Code-Text Transformer.pdf b/papers/CoTexT: Multi-task Learning with Code-Text Transformer.pdf new file mode 100644 index 0000000000000000000000000000000000000000..609a65f56b24cb76de812adcd2ef1822343c9c12 --- /dev/null +++ b/papers/CoTexT: Multi-task Learning with Code-Text Transformer.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703e40ceeb43158a1cbaf5afb99f575bf6defd776381249f1f6bf3686206b1fc +size 163833 diff --git a/papers/CodeBERT: A Pre-Trained Model for Programming and Natural Languages.pdf b/papers/CodeBERT: A Pre-Trained Model for Programming and Natural Languages.pdf new file mode 100644 index 0000000000000000000000000000000000000000..5a01bcd79dc95324974235f9b74ad35483733a81 --- /dev/null +++ b/papers/CodeBERT: A Pre-Trained Model for Programming and Natural Languages.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4208bcf8747cf7e8dfa14ed09e856b7fa0a20f45613692c11ce458791ae31b84 +size 465537 diff --git a/papers/CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X.pdf b/papers/CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X.pdf new file mode 100644 index 0000000000000000000000000000000000000000..2be256c0a4fbe979b9203d3c464121a2a3772764 --- /dev/null +++ b/papers/CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb5681999075d5a922871da8308b5e68ccf7997cbdfa3a71f3a3291079e88d0 +size 3873166 diff --git a/papers/CodeGemma Open Code Models Based on Gemma.pdf b/papers/CodeGemma Open Code Models Based on Gemma.pdf new file mode 100644 index 0000000000000000000000000000000000000000..65fe4638504b24b82efafe3bb42f126e4cbd7f1a --- /dev/null +++ b/papers/CodeGemma Open Code Models Based on Gemma.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63b6582424f1feff5ca7fa03f511a4ec6b8b692a4550a50f8f62058e99de585d +size 222988 diff --git a/papers/CodeT5+: Open Code Large Language Models for Code Understanding and Generation.pdf b/papers/CodeT5+: Open Code Large Language Models for Code Understanding and Generation.pdf new file mode 100644 index 0000000000000000000000000000000000000000..0bf3a7b56914bf9dad2fce8e1457a907d276af97 --- /dev/null +++ b/papers/CodeT5+: Open Code Large Language Models for Code Understanding and Generation.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b0584d3de3784f2f8d6e49592a8fb65b0d94455cf98156adca1d28262c91d54 +size 695855 diff --git a/papers/Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT.pdf b/papers/Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT.pdf new file mode 100644 index 0000000000000000000000000000000000000000..d0093ccdf78af1dc92a17f87b1fc5b2ffa01a5ee --- /dev/null +++ b/papers/Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b0d4ea27779a59d16f6cdbd6b6b8abcc137d338cc6cadb2c60c9bca7c61d5c +size 1214009 diff --git a/papers/GRAPH CODE BERT: PRE-TRAINING CODE REPRESEN-TATIONS WITH DATA F LOW.pdf b/papers/GRAPH CODE BERT: PRE-TRAINING CODE REPRESEN-TATIONS WITH DATA F LOW.pdf new file mode 100644 index 0000000000000000000000000000000000000000..942125520881dae9bcab464674832caafab0503b --- /dev/null +++ b/papers/GRAPH CODE BERT: PRE-TRAINING CODE REPRESEN-TATIONS WITH DATA F LOW.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574a41f6c8d94dfec9202424319654aad7f9014eebb32d7037c2e040894b764c +size 685074 diff --git a/papers/StructCoder_ Structure-Aware Transformer for Code Generation - 2206.05239v3.pdf b/papers/StructCoder_ Structure-Aware Transformer for Code Generation - 2206.05239v3.pdf new file mode 100644 index 0000000000000000000000000000000000000000..23d30d343e5540a8ea07ffcc1cb6704797c877c4 --- /dev/null +++ b/papers/StructCoder_ Structure-Aware Transformer for Code Generation - 2206.05239v3.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2834776aece3516b287b4667f725d1e8aec968283abca06b27b098fc78f0a839 +size 733827 diff --git a/papers/TreeGen: A Tree-Based Transformer Architecture for Code Generation.pdf b/papers/TreeGen: A Tree-Based Transformer Architecture for Code Generation.pdf new file mode 100644 index 0000000000000000000000000000000000000000..53c65a5c8e335e8f2d9544313f3926bb1cabef5f --- /dev/null +++ b/papers/TreeGen: A Tree-Based Transformer Architecture for Code Generation.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18bc60048d5baf97778693146d62e5d32ff3959d5c76ec159ae126b9496e8ab +size 379513 diff --git a/project.ipynb b/project.ipynb new file mode 100644 index 0000000000000000000000000000000000000000..6a0155e5a8da552282b64446d551e4d66551d7a7 --- /dev/null +++ b/project.ipynb @@ -0,0 +1,482 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "3e7c79bb", + "metadata": {}, + "source": [ + "# MiniCoderX Project - Full Pipeline Notebook" + ] + }, + { + "cell_type": "markdown", + "id": "82aa402a", + "metadata": {}, + "source": [ + "# Step 0: Environment Setup" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fe661c57", + "metadata": {}, + "outputs": [], + "source": [ + "pip install -q tokenizers transformers datasets sentencepiece langchain_community ollama networkx evaluate rouge_score matplotlib seaborn lark fastapi uvicorn" + ] + }, + { + "cell_type": "markdown", + "id": "7313bed0", + "metadata": {}, + "source": [ + "# Step 1: Import and Load Model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2e28b42b", + "metadata": {}, + "outputs": [], + "source": [ + "from tokenizers import Tokenizer, models, trainers, pre_tokenizers\n", + "from tokenizers.normalizers import Sequence, Lowercase, NFD, StripAccents\n", + "from tokenizers.pre_tokenizers import Whitespace\n", + "from tokenizers.processors import TemplateProcessing\n", + "from transformers import PreTrainedTokenizerFast\n", + "import os\n", + "\n", + "tokenizer = Tokenizer(models.BPE())\n", + "tokenizer.normalizer = Sequence([NFD(), Lowercase(), StripAccents()])\n", + "tokenizer.pre_tokenizer = Whitespace()\n", + "\n", + "trainer = trainers.BpeTrainer(\n", + " vocab_size=32000,\n", + " special_tokens=[\"\", \"\", \"\", \"\", \"\"]\n", + ")\n", + "\n", + "data_path = \"data/code_corpus.txt\"\n", + "\n", + "if not os.path.exists(data_path):\n", + " raise FileNotFoundError(f\"Dataset not found at: {data_path}\")\n", + "else:\n", + " print(\"Dataset found:\", data_path)\n", + "\n", + "tokenizer.train([data_path], trainer)\n", + "\n", + "\n", + "tokenizer.post_processor = TemplateProcessing(\n", + " single=\" $A \",\n", + " pair=\" $A $B \",\n", + " special_tokens=[\n", + " (\"\", tokenizer.token_to_id(\"\")),\n", + " (\"\", tokenizer.token_to_id(\"\")),\n", + " ],\n", + ")\n", + "\n", + "tokenizer_path = \"minicoderx-tokenizer\"\n", + "os.makedirs(tokenizer_path, exist_ok=True)\n", + "tokenizer.save(f\"{tokenizer_path}/tokenizer.json\")\n", + "print(\"Tokenizer saved to:\", tokenizer_path)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d1ab6421", + "metadata": {}, + "outputs": [], + "source": [ + "from transformers import PreTrainedTokenizerFast\n", + "\n", + "hf_tokenizer = PreTrainedTokenizerFast(\n", + " tokenizer_file=\"minicoderx-tokenizer/tokenizer.json\",\n", + " unk_token=\"\",\n", + " pad_token=\"\",\n", + " cls_token=\"\",\n", + " sep_token=\"\",\n", + " mask_token=\"\",\n", + ")\n", + "\n", + "hf_tokenizer.save_pretrained(\"minicoderx-tokenizer\")\n", + "print(\"HuggingFace tokenizer saved and ready.\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "ba28e05f", + "metadata": {}, + "outputs": [], + "source": [ + "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n", + "\n", + "# Load your trained model and tokenizer\n", + "tokenizer = AutoTokenizer.from_pretrained(\"minicoderx-model\")\n", + "model = AutoModelForSeq2SeqLM.from_pretrained(\"minicoderx-model\")\n", + "\n", + "print(\"Model and tokenizer loaded.\")" + ] + }, + { + "cell_type": "markdown", + "id": "852b82c3", + "metadata": {}, + "source": [ + "# Step 2: Inference - Code Generation" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6ab29f13", + "metadata": {}, + "outputs": [], + "source": [ + "input_text = \"Write a Python function to compute factorial\"\n", + "inputs = tokenizer(input_text, return_tensors=\"pt\")\n", + "outputs = model.generate(**inputs, max_length=128)\n", + "print(\"\\nGenerated Code:\\n\")\n", + "print(tokenizer.decode(outputs[0], skip_special_tokens=True))" + ] + }, + { + "cell_type": "markdown", + "id": "e2e495b0", + "metadata": {}, + "source": [ + "# Step 3: Structure-Aware Encoding with AST" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c5337fe3", + "metadata": {}, + "outputs": [], + "source": [ + "import ast, networkx as nx, matplotlib.pyplot as plt, seaborn as sns\n", + "\n", + "def build_ast_graph_with_metadata(node, graph, parent=None):\n", + " node_id = str(id(node))\n", + " graph.add_node(node_id, label=type(node).__name__)\n", + " if parent:\n", + " graph.add_edge(parent, node_id)\n", + " for child in ast.iter_child_nodes(node):\n", + " build_ast_graph_with_metadata(child, graph, node_id)\n", + "\n", + "code_sample = \"\"\"\n", + "def add(a, b):\n", + " return a + b\n", + "\"\"\"\n", + "tree = ast.parse(code_sample)\n", + "G = nx.DiGraph()\n", + "build_ast_graph_with_metadata(tree, G)\n", + "pos = nx.spring_layout(G)\n", + "labels = nx.get_node_attributes(G, 'label')\n", + "nx.draw(G, pos, labels=labels, with_labels=True, node_size=1200, node_color='lightblue')\n", + "plt.title(\"AST Visualization\")\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "f732a8cf", + "metadata": {}, + "source": [ + "# Step 4: LangChain + Ollama Integration" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0b2c013c", + "metadata": {}, + "outputs": [], + "source": [ + "from langchain_community.llms import Ollama\n", + "from langchain.chains import LLMChain\n", + "from langchain.prompts import PromptTemplate\n", + "\n", + "llm = Ollama(model=\"minicoderx\")\n", + "prompt = PromptTemplate(input_variables=[\"instruction\"], template=\"Generate Python code for the task: {instruction}\")\n", + "chain = LLMChain(llm=llm, prompt=prompt)\n", + "print(\"\\nLangChain-Ollama Output:\")\n", + "print(chain.run(\"Create a function to reverse a string\"))" + ] + }, + { + "cell_type": "markdown", + "id": "6ded4c5e", + "metadata": {}, + "source": [ + "# Step 5: Evaluation (MBPP)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "37f133a4", + "metadata": {}, + "outputs": [], + "source": [ + "from datasets import load_dataset\n", + "import evaluate\n", + "\n", + "dataset = load_dataset(\"mbpp\")\n", + "eval_bleu = evaluate.load(\"bleu\")\n", + "eval_rouge = evaluate.load(\"rouge\")\n", + "\n", + "sample = dataset['test'][0]\n", + "input_text = f\"Write a Python function: {sample['text']}\"\n", + "inputs = tokenizer(input_text, return_tensors=\"pt\")\n", + "output = model.generate(**inputs, max_length=128)\n", + "generated_code = tokenizer.decode(output[0], skip_special_tokens=True)\n", + "\n", + "print(\"\\nEvaluation Sample Output:\\n\", generated_code)\n", + "print(\"BLEU:\", eval_bleu.compute(predictions=[generated_code], references=[sample['code']]))\n", + "print(\"ROUGE:\", eval_rouge.compute(predictions=[generated_code], references=[sample['code']]))" + ] + }, + { + "cell_type": "markdown", + "id": "2b00a47c", + "metadata": {}, + "source": [ + "# Step 6: Testing, Verification, and Unit Test Gen" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a9a8ef01", + "metadata": {}, + "outputs": [], + "source": [ + "import tempfile, subprocess\n", + "\n", + "def run_code(code, test_case):\n", + " with tempfile.NamedTemporaryFile(mode='w+', suffix='.py', delete=False) as tmp:\n", + " tmp.write(code + '\\n' + test_case)\n", + " tmp.flush()\n", + " result = subprocess.run(['python', tmp.name], capture_output=True, text=True)\n", + " print(\"Output:\\n\", result.stdout)\n", + " if result.stderr:\n", + " print(\"Errors:\\n\", result.stderr)\n", + "\n", + "test_case = \"print(factorial(5)) # Expected: 120\"\n", + "run_code(generated_code, test_case)\n", + "\n", + "unit_prompt = PromptTemplate(input_variables=[\"code\"], template=\"Write a unittest in Python for the following function:\\n\\n{code}\")\n", + "unit_chain = LLMChain(llm=llm, prompt=unit_prompt)\n", + "print(\"\\nGenerated Unit Test:\\n\", unit_chain.run(code=generated_code))" + ] + }, + { + "cell_type": "markdown", + "id": "9b9fcc1e", + "metadata": {}, + "source": [ + "# Step 7: Safety and Grammar Constraints" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5e3dd5ee", + "metadata": {}, + "outputs": [], + "source": [ + "from lark import Lark, UnexpectedInput\n", + "\n", + "python_grammar = \"\"\"\n", + "start: stmt+\n", + "stmt: \"def\" NAME \"(\" [params] \")\" \":\" suite\n", + "params: NAME (\",\" NAME)*\n", + "suite: NEWLINE INDENT stmt+ DEDENT | simple_stmt\n", + "simple_stmt: NAME \"=\" expr NEWLINE\n", + "expr: atom | atom operator atom\n", + "atom: NAME | NUMBER\n", + "operator: \"+\" | \"-\" | \"*\" | \"/\"\n", + "%import common.CNAME -> NAME\n", + "%import common.NUMBER\n", + "%import common.NEWLINE\n", + "%import common.WS_INLINE\n", + "%import common.INDENT\n", + "%import common.DEDENT\n", + "%ignore WS_INLINE\n", + "\"\"\"\n", + "\n", + "parser = Lark(python_grammar, parser=\"lalr\")\n", + "\n", + "unsafe_keywords = [\"os.system\", \"subprocess\", \"eval\", \"exec\", \"open(\", \"import socket\"]\n", + "print(\"\\nSafety Check:\")\n", + "print(\"Unsafe pattern found\" if any(k in generated_code for k in unsafe_keywords) else \"Code is safe\")\n", + "\n", + "print(\"\\nGrammar Check:\")\n", + "try:\n", + " parser.parse(generated_code)\n", + " print(\"Code grammar is valid.\")\n", + "except UnexpectedInput as e:\n", + " print(\"Grammar error:\", e)" + ] + }, + { + "cell_type": "markdown", + "id": "8b1e2b86", + "metadata": {}, + "source": [ + "# Step 8: Multi-Task Preprocessing (gen, sum, trans)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "09a12f1d", + "metadata": {}, + "outputs": [], + "source": [ + "def preprocess_multitask(example):\n", + " if example['task'] == 'gen':\n", + " input_text = f\"Write code: {example['text']}\"\n", + " output_text = example['code']\n", + " elif example['task'] == 'sum':\n", + " input_text = f\"Summarize this code: {example['code']}\"\n", + " output_text = example['text']\n", + " elif example['task'] == 'trans':\n", + " input_text = f\"Translate Java to Python: {example['java']}\"\n", + " output_text = example['python']\n", + " else:\n", + " input_text, output_text = example['text'], example['code']\n", + " model_input = tokenizer(input_text, max_length=128, truncation=True)\n", + " with tokenizer.as_target_tokenizer():\n", + " labels = tokenizer(output_text, max_length=128, truncation=True)\n", + " model_input['labels'] = labels['input_ids']\n", + " return model_input" + ] + }, + { + "cell_type": "markdown", + "id": "6018db4c", + "metadata": {}, + "source": [ + "# Step 9: Fine-Tuning Setup" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c15ad38d", + "metadata": {}, + "outputs": [], + "source": [ + "from transformers import Seq2SeqTrainer, Seq2SeqTrainingArguments, DataCollatorForSeq2Seq\n", + "\n", + "train_dataset = dataset[\"train\"].map(preprocess_multitask, remove_columns=dataset[\"train\"].column_names)\n", + "val_dataset = dataset[\"validation\"].map(preprocess_multitask, remove_columns=dataset[\"validation\"].column_names)\n", + "\n", + "training_args = Seq2SeqTrainingArguments(\n", + " output_dir=\"./minicoderx-finetuned\",\n", + " evaluation_strategy=\"epoch\",\n", + " learning_rate=5e-5,\n", + " per_device_train_batch_size=8,\n", + " per_device_eval_batch_size=8,\n", + " weight_decay=0.01,\n", + " save_total_limit=2,\n", + " num_train_epochs=3,\n", + " predict_with_generate=True,\n", + " logging_dir=\"./logs\",\n", + " logging_steps=10,\n", + ")\n", + "\n", + "data_collator = DataCollatorForSeq2Seq(tokenizer, model=model)\n", + "trainer = Seq2SeqTrainer(\n", + " model=model,\n", + " args=training_args,\n", + " train_dataset=train_dataset,\n", + " eval_dataset=val_dataset,\n", + " tokenizer=tokenizer,\n", + " data_collator=data_collator,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "28d3dcb1", + "metadata": {}, + "outputs": [], + "source": [ + "# Uncomment to run training\n", + "# trainer.train()\n", + "# trainer.save_model(\"./minicoderx-finetuned\")" + ] + }, + { + "cell_type": "markdown", + "id": "8c4d0d79", + "metadata": {}, + "source": [ + "# Step 10: Deploy with FastAPI" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3f239ed4", + "metadata": {}, + "outputs": [], + "source": [ + "from fastapi import FastAPI\n", + "from pydantic import BaseModel\n", + "import uvicorn\n", + "\n", + "app = FastAPI()\n", + "\n", + "class CodeRequest(BaseModel):\n", + " instruction: str\n", + "\n", + "@app.post(\"/generate\")\n", + "def generate_code(req: CodeRequest):\n", + " inputs = tokenizer(req.instruction, return_tensors=\"pt\")\n", + " outputs = model.generate(**inputs, max_length=128)\n", + " code = tokenizer.decode(outputs[0], skip_special_tokens=True)\n", + " return {\"code\": code}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "33ec10a2", + "metadata": {}, + "outputs": [], + "source": [ + "# Uncomment to run API\n", + "# uvicorn.run(app, host=\"0.0.0.0\", port=8000)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "myenv", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.16" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/train_t5_code.py b/train_t5_code.py new file mode 100644 index 0000000000000000000000000000000000000000..baae59363f1262663494f65183297294395bc36c --- /dev/null +++ b/train_t5_code.py @@ -0,0 +1,65 @@ +from transformers import T5TokenizerFast, T5ForConditionalGeneration, Trainer, TrainingArguments, DataCollatorForSeq2Seq +from datasets import load_dataset, Dataset +import os +import json + +# === Load your custom tokenizer === +tokenizer = T5TokenizerFast.from_pretrained("minicoderx-tokenizer") + +# === Load or create dataset === +def load_jsonl(path): + with open(path) as f: + data = [json.loads(line) for line in f] + return Dataset.from_dict({ + "input": [x["input"] for x in data], + "output": [x["output"] for x in data] + }) + +dataset = load_jsonl("data/train.jsonl") + +# === Tokenize dataset === +def tokenize(batch): + return tokenizer(batch["input"], padding="max_length", truncation=True, max_length=128) + +def tokenize_labels(batch): + labels = tokenizer(batch["output"], padding="max_length", truncation=True, max_length=128) + batch["labels"] = labels["input_ids"] + return batch + +dataset = dataset.map(tokenize) +dataset = dataset.map(tokenize_labels) + +# === Load pre-trained T5-small === +model = T5ForConditionalGeneration.from_pretrained("t5-small") + +# === Training configuration === +training_args = TrainingArguments( + output_dir="minicoderx-model", + per_device_train_batch_size=4, + num_train_epochs=3, + logging_steps=10, + save_strategy="epoch", + evaluation_strategy="no", + save_total_limit=2, + fp16=True, + overwrite_output_dir=True, +) + +data_collator = DataCollatorForSeq2Seq(tokenizer, model=model) + +trainer = Trainer( + model=model, + args=training_args, + train_dataset=dataset, + data_collator=data_collator, + tokenizer=tokenizer +) + +# === Train === +trainer.train() + +# === Save model === +trainer.save_model("minicoderx-model") +tokenizer.save_pretrained("minicoderx-model") + +print("Training complete and model saved.") \ No newline at end of file diff --git a/wandb/run-20250501_201730-n8bj3yj1/files/config.yaml b/wandb/run-20250501_201730-n8bj3yj1/files/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..17c09df5a20eb7c9a1d9ea1777d43c2c11780e15 --- /dev/null +++ b/wandb/run-20250501_201730-n8bj3yj1/files/config.yaml @@ -0,0 +1,506 @@ +_attn_implementation_autoset: + value: true +_name_or_path: + value: t5-small +_wandb: + value: + cli_version: 0.19.10 + m: + - "1": train/global_step + "6": + - 3 + "7": [] + - "1": train/epoch + "5": 1 + "6": + - 1 + - 3 + "7": [] + python_version: 3.10.16 + t: + "1": + - 1 + - 5 + - 11 + - 49 + - 51 + - 53 + - 55 + - 71 + - 98 + - 105 + "2": + - 1 + - 5 + - 11 + - 49 + - 51 + - 53 + - 55 + - 71 + - 98 + - 105 + "3": + - 7 + - 13 + - 19 + - 23 + - 55 + - 62 + - 66 + "4": 3.10.16 + "5": 0.19.10 + "6": 4.49.0 + "8": + - 5 + "9": + "1": transformers_trainer + "12": 0.19.10 + "13": linux-x86_64 +accelerator_config: + value: + dispatch_batches: null + even_batches: true + gradient_accumulation_kwargs: null + non_blocking: false + split_batches: false + use_seedable_sampler: true +adafactor: + value: false +adam_beta1: + value: 0.9 +adam_beta2: + value: 0.999 +adam_epsilon: + value: 1e-08 +add_cross_attention: + value: false +architectures: + value: + - T5ForConditionalGeneration +auto_find_batch_size: + value: false +average_tokens_across_devices: + value: false +bad_words_ids: + value: null +batch_eval_metrics: + value: false +begin_suppress_tokens: + value: null +bf16: + value: false +bf16_full_eval: + value: false +bos_token_id: + value: null +chunk_size_feed_forward: + value: 0 +classifier_dropout: + value: 0 +cross_attention_hidden_size: + value: null +d_ff: + value: 2048 +d_kv: + value: 64 +d_model: + value: 512 +data_seed: + value: null +dataloader_drop_last: + value: false +dataloader_num_workers: + value: 0 +dataloader_persistent_workers: + value: false +dataloader_pin_memory: + value: true +dataloader_prefetch_factor: + value: null +ddp_backend: + value: null +ddp_broadcast_buffers: + value: null +ddp_bucket_cap_mb: + value: null +ddp_find_unused_parameters: + value: null +ddp_timeout: + value: 1800 +debug: + value: [] +decoder_start_token_id: + value: 0 +deepspeed: + value: null +dense_act_fn: + value: relu +disable_tqdm: + value: false +dispatch_batches: + value: null +diversity_penalty: + value: 0 +do_eval: + value: false +do_predict: + value: false +do_sample: + value: false +do_train: + value: false +dropout_rate: + value: 0.1 +early_stopping: + value: false +encoder_no_repeat_ngram_size: + value: 0 +eos_token_id: + value: 1 +eval_accumulation_steps: + value: null +eval_delay: + value: 0 +eval_do_concat_batches: + value: true +eval_on_start: + value: false +eval_steps: + value: null +eval_strategy: + value: "no" +eval_use_gather_object: + value: false +evaluation_strategy: + value: "no" +exponential_decay_length_penalty: + value: null +feed_forward_proj: + value: relu +finetuning_task: + value: null +forced_bos_token_id: + value: null +forced_eos_token_id: + value: null +fp16: + value: true +fp16_backend: + value: auto +fp16_full_eval: + value: false +fp16_opt_level: + value: O1 +fsdp: + value: [] +fsdp_config: + value: + min_num_params: 0 + xla: false + xla_fsdp_grad_ckpt: false + xla_fsdp_v2: false +fsdp_min_num_params: + value: 0 +fsdp_transformer_layer_cls_to_wrap: + value: null +full_determinism: + value: false +gradient_accumulation_steps: + value: 1 +gradient_checkpointing: + value: false +gradient_checkpointing_kwargs: + value: null +greater_is_better: + value: null +group_by_length: + value: false +half_precision_backend: + value: auto +hub_always_push: + value: false +hub_model_id: + value: null +hub_private_repo: + value: null +hub_strategy: + value: every_save +hub_token: + value: +id2label: + value: + "0": LABEL_0 + "1": LABEL_1 +ignore_data_skip: + value: false +include_for_metrics: + value: [] +include_inputs_for_metrics: + value: false +include_num_input_tokens_seen: + value: false +include_tokens_per_second: + value: false +initializer_factor: + value: 1 +is_decoder: + value: false +is_encoder_decoder: + value: true +is_gated_act: + value: false +jit_mode_eval: + value: false +label_names: + value: null +label_smoothing_factor: + value: 0 +label2id: + value: + LABEL_0: 0 + LABEL_1: 1 +layer_norm_epsilon: + value: 1e-06 +learning_rate: + value: 5e-05 +length_column_name: + value: length +length_penalty: + value: 1 +load_best_model_at_end: + value: false +local_rank: + value: 0 +log_level: + value: passive +log_level_replica: + value: warning +log_on_each_node: + value: true +logging_dir: + value: minicoderx-model/runs/May01_20-12-15_IRIE +logging_first_step: + value: false +logging_nan_inf_filter: + value: true +logging_steps: + value: 10 +logging_strategy: + value: steps +lr_scheduler_type: + value: linear +max_grad_norm: + value: 1 +max_length: + value: 20 +max_steps: + value: -1 +metric_for_best_model: + value: null +min_length: + value: 0 +model/num_parameters: + value: 60506624 +model_type: + value: t5 +mp_parameters: + value: "" +n_positions: + value: 512 +neftune_noise_alpha: + value: null +no_cuda: + value: false +no_repeat_ngram_size: + value: 0 +num_beam_groups: + value: 1 +num_beams: + value: 1 +num_decoder_layers: + value: 6 +num_heads: + value: 8 +num_layers: + value: 6 +num_return_sequences: + value: 1 +num_train_epochs: + value: 3 +optim: + value: adamw_torch +optim_args: + value: null +optim_target_modules: + value: null +output_attentions: + value: false +output_dir: + value: minicoderx-model +output_hidden_states: + value: false +output_past: + value: true +output_scores: + value: false +overwrite_output_dir: + value: true +pad_token_id: + value: 0 +past_index: + value: -1 +per_device_eval_batch_size: + value: 8 +per_device_train_batch_size: + value: 4 +per_gpu_eval_batch_size: + value: null +per_gpu_train_batch_size: + value: null +prediction_loss_only: + value: false +prefix: + value: null +problem_type: + value: null +push_to_hub: + value: false +push_to_hub_model_id: + value: null +push_to_hub_organization: + value: null +push_to_hub_token: + value: +ray_scope: + value: last +relative_attention_max_distance: + value: 128 +relative_attention_num_buckets: + value: 32 +remove_invalid_values: + value: false +remove_unused_columns: + value: true +repetition_penalty: + value: 1 +report_to: + value: + - wandb +restore_callback_states_from_checkpoint: + value: false +resume_from_checkpoint: + value: null +return_dict: + value: true +return_dict_in_generate: + value: false +run_name: + value: minicoderx-model +save_on_each_node: + value: false +save_only_model: + value: false +save_safetensors: + value: true +save_steps: + value: 500 +save_strategy: + value: epoch +save_total_limit: + value: 2 +seed: + value: 42 +sep_token_id: + value: null +skip_memory_metrics: + value: true +split_batches: + value: null +suppress_tokens: + value: null +task_specific_params: + value: + summarization: + early_stopping: true + length_penalty: 2 + max_length: 200 + min_length: 30 + no_repeat_ngram_size: 3 + num_beams: 4 + prefix: 'summarize: ' + translation_en_to_de: + early_stopping: true + max_length: 300 + num_beams: 4 + prefix: 'translate English to German: ' + translation_en_to_fr: + early_stopping: true + max_length: 300 + num_beams: 4 + prefix: 'translate English to French: ' + translation_en_to_ro: + early_stopping: true + max_length: 300 + num_beams: 4 + prefix: 'translate English to Romanian: ' +temperature: + value: 1 +tf_legacy_loss: + value: false +tf32: + value: null +tie_encoder_decoder: + value: false +tie_word_embeddings: + value: true +tokenizer_class: + value: null +top_k: + value: 50 +top_p: + value: 1 +torch_compile: + value: false +torch_compile_backend: + value: null +torch_compile_mode: + value: null +torch_dtype: + value: float32 +torch_empty_cache_steps: + value: null +torchdynamo: + value: null +torchscript: + value: false +tpu_metrics_debug: + value: false +tpu_num_cores: + value: null +transformers_version: + value: 4.49.0 +typical_p: + value: 1 +use_bfloat16: + value: false +use_cache: + value: true +use_cpu: + value: false +use_ipex: + value: false +use_legacy_prediction_loop: + value: false +use_liger_kernel: + value: false +use_mps_device: + value: false +vocab_size: + value: 32128 +warmup_ratio: + value: 0 +warmup_steps: + value: 0 +weight_decay: + value: 0 diff --git a/wandb/run-20250501_201730-n8bj3yj1/files/output.log b/wandb/run-20250501_201730-n8bj3yj1/files/output.log new file mode 100644 index 0000000000000000000000000000000000000000..b089629eb76c1534c50e9d4893c7974710332cfa --- /dev/null +++ b/wandb/run-20250501_201730-n8bj3yj1/files/output.log @@ -0,0 +1,4 @@ + 0%| | 0/3 [00:00', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'no', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False} +2025-05-01 20:17:32,170 INFO MainThread:84815 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 60506624 - > +2025-05-01 20:17:32,170 INFO MainThread:84815 [wandb_run.py:_config_callback():1429] config_cb model/num_parameters 60506624 None +2025-05-01 20:17:54,369 INFO MsgRouterThr:84815 [mailbox.py:close():129] [no run ID] Closing mailbox, abandoning 1 handles. diff --git a/wandb/run-20250501_201730-n8bj3yj1/run-n8bj3yj1.wandb b/wandb/run-20250501_201730-n8bj3yj1/run-n8bj3yj1.wandb new file mode 100644 index 0000000000000000000000000000000000000000..42a238833f54598e4b1931f502b738946973726d Binary files /dev/null and b/wandb/run-20250501_201730-n8bj3yj1/run-n8bj3yj1.wandb differ