model upload

README.md

@@ -0,0 +1,101 @@
+---
+license: llama2
+model-index:
+- name: ETRI-CodeLLaMA-7B-CPP
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: HumanEval-X
+      name: humanevalsynthesize-cpp
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 34.3%
+      verified: false
+tags:
+- code llama
+---
+
+## **ETRI-CodeLLaMA-7B-CPP**
+
+We used LoRa to further pre-train Meta's CodeLLaMA-7B-hf model with high-quality C++ code tokens.
+
+Furthermore, we was fine-tuned on CodeM's C++ instruction data.
+
+## Model Details
+
+This model was trained using LoRa and achieved a pass@1 of 34.3% on HumanEvalX-cpp.
+
+ETRI-CodeLLaMA-7B-CPP is a C++ specialized model.
+
+## Dataset Details
+
+We pre-trained CodeLLaMA-7B further using 543 GB of C++ code collected online, and fine-tuned it using CodeM's C++ instruction data. We utilized four A100-80GB GPUs for the training.
+
+## Requirements
+
+```
+peft==0.3.0.dev0 
+tokenizers==0.13.3 
+transformers==4.33.0 
+bitsandbytes==0.41.1
+```
+
+## How to reproduce HumanEval-X results
+
+We use Bigcode-evaluation-harness repo for evaluating our trained model.
+
+bigcode-evaluation-harness
+
+```
+git clone https://github.com/bigcode-project/bigcode-evaluation-harness.git
+```
+
+Then, run main.py as follows.
+
+```
+accelerate launch bigcode-evaluation-harness/main.py \
+  --model DDIDU/ETRI-CodeLLaMA-7B-CPP \
+  --max_length_generation 512 \
+  --prompt continue \
+  --tasks humanevalsynthesize-cpp \
+  --temperature 0.2 \
+  --n_samples 100 \
+  --precision bf16 \
+  --do_sample True \
+  --batch_size 10 \
+  --allow_code_execution \
+  --save_generations \
+```
+
+## Model use
+
+```
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "DDIDU/ETRI-CodeLLaMA-7B-CPP"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+sequences = pipeline(
+    'import socket\n\ndef ping_exponential_backoff(host: str):',
+    do_sample=True,
+    top_k=10,
+    temperature=0.1,
+    top_p=0.95,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+    max_length=200,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.2"
+}

pytorch_model-00001-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16592d85f5be310d8bf166772f8bb717aa83528584b061a6ce543c77b078f53
+size 981620682

pytorch_model-00002-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fab08d2181263df59ac894c6a67c303f60c890a9d1ae34650eca8c5037b84ce
+size 966844488

pytorch_model-00003-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5cda5afb3b22d3fa47e426959514ad1fbb7f3d42e359e046ad4d997cd26b973
+size 966827492

pytorch_model-00004-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478d4ccb69cfcde82ef0b3ecc38f14e21c60d40b7e1a7f2ae599a9e663a0f9fb
+size 989912886

pytorch_model-00005-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33dc9da053e737353ede8ac5203412af570d98358111357b13e96e03da545784
+size 943759158

pytorch_model-00006-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c25e5355aab888d01f99e270df11ea35f6e40c9e959eea22039f94a771f203
+size 989895890

pytorch_model-00007-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65dcef6d4497d9c7bb548015e88f5a99a0a463bc30b1cc151608e67199eacd3d
+size 966844552

pytorch_model-00008-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8279fee22af55dc1f49dbed1a52d7f0b01ad60c1fd181470c4d2811ec837c62b
+size 966827556

pytorch_model-00009-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7951dcb6f624023be7d8b3df8bac9e2e834b87cd596b860131e481e69b442ce6
+size 989912886

pytorch_model-00010-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f1d9a7360417b4347e2b51dea1e5a37f8a44ed32794f22927678291e976fe5
+size 943759158

pytorch_model-00011-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61608b93a0768ac5d5e83e748385cdd33d4a5f85b6d31b41b245f23557539ef
+size 989895890

pytorch_model-00012-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a1534a4ecbb7e01a886069578367c97bd04a19a5058066fe9bb463f5d73717
+size 966844552

pytorch_model-00013-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c8ff87e70395011584a65829fb5a5f14b373e783737b9a939410b6beebe6bf
+size 966827556

pytorch_model-00014-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3025ea2c6a4fa377cb43c219738ce7d49e5a6caf88ec04d61039778aeeaf8a0
+size 847427192

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13477093376
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00014-of-00014.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00014.bin"
+  }
+}