Upload folder using huggingface_hub

config.json

@@ -1,25 +1,42 @@
 {
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 5120,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 13824,
+  "intermediate_size": 11008,
   "max_position_embeddings": 4096,
   "model_type": "llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "pad_token_id": 0,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
-  "use_cache": false,
-  "vocab_size": 32002
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
 }

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d8140055919d96001f650b71d3d253ca54c8bf8a79cae8c509e0fa1ecf05db
-size 7866132240
+oid sha256:52f3d0ad48c5e9e1139b0be6185dd36861b3e2d34966cf47e9f60c347bac2ab5
+size 3866042080