Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "daryl149/llama-2-7b-chat-hf",
+  "_name_or_path": "NousResearch/llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,17 +9,17 @@
   "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,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000

generation_config.json

@@ -2,6 +2,8 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 0,
+  "pad_token_id": 32000,
+  "temperature": 0.9,
+  "top_p": 0.6,
   "transformers_version": "4.31.0"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9c768c284b90e1e1d724b9b1becd6e48bf52fa06d350c40d98353e5d622825
-size 9976637886
+oid sha256:f6ae1434ebd61c292fe7a4d5cbb4bf484612a232ebe78f18b64bdf4455b37a6f
+size 9976637950

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb33599b09b0bf025f58e2d34c4c5d53f5f3946b10f72d66d9b9d59b1532410d
+oid sha256:6fa6d61e7c6dade6906e9d2cb9a74d49e35e2ef15ba11a94c159ee0ae15d49b1
 size 3500316627