Upload LlamaForCausalLM

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/home/common/data/Big_Data/GenAI/llm_models/NousResearch--CodeLlama-7b-hf",
+  "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,
+  "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": "float32",
+  "transformers_version": "4.34.0",
+  "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": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7564899a26e78f74217757869b5f5ef44b32bc85b73243b3aac00f8a839b8aa
+size 4490636333