Upload LlamaForCausalLM

config.json

@@ -1,34 +1,29 @@
 {
-  "_name_or_path": "/home/common/data/Big_Data/GenAI/llm_models/NousResearch--CodeLlama-7b-hf",
+  "_name_or_path": "/home/common/data/Big_Data/GenAI/llm_models/openlm-research--open_llama_3b_v2",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
-  "auto_map": {
-    "AutoConfig": "NousResearch/CodeLlama-7b-hf--configuration_llama.LlamaConfig",
-    "AutoModel": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaModel",
-    "AutoModelForCausalLM": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaForCausalLM",
-    "AutoModelForSequenceClassification": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaForSequenceClassification"
-  },
   "bigdl_transformers_low_bit": "sym_int4",
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 3200,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 16384,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 26,
   "num_key_value_heads": 32,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
   "use_cache": true,
-  "vocab_size": 32016
+  "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.34.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7564899a26e78f74217757869b5f5ef44b32bc85b73243b3aac00f8a839b8aa
-size 4490636333
+oid sha256:e1972397dbb0b378310524acbd180502278c45dc246e9a7e8c7502d7787c8d6e
+size 2531378049