Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/media/Blue2TB3/jpei/transformer_data/llama-2-7b-chat",
+  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,14 +11,13 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,

generation_config.json

@@ -1,7 +1,10 @@
 {
-  "_from_model_config": true,
   "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": "4.36.1"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c696ae904c45b111b1c998925fbc9a40934212ce3d15efa266ee975ae4a16c1
+oid sha256:ecadde92cfacaea9570098248692c709461404045287448a9fb1c8bd7d9f0b43
 size 4938985352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671786b0467a6193f0626754023692e6ec251e85714891bebea138d6a35b8935
+oid sha256:6e1708abcf839e461ef804d701fc4173c16d1bc7fd054766573ccfa3e77cd31a
 size 4947390880

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ea671792f021845054c9d40bd44dd0107f322304bad1a8596be125e43acecc
+oid sha256:f6fb19236fc32c397a19dc8a74236e3ef6d0102e17cdc5830313f1909d35af37
 size 3590488816