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"
   ],
@@ -9,14 +9,14 @@
   "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",

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:dffe1d430ffabdbbdb41c04cb7ae66e6a0729556efbd4ec935fdc88a4f133ad3
+oid sha256:fa43e52ac7a1b4738baaae45b0353e0148588362835a1cb22467adc07671abcf
 size 9976637886

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7f4ea66d24ca804710700e5c887b08e00d3a2d7e257b67bba35188147b418c
+oid sha256:78636aa135fb258992534b2589b4b3f2ce12f8c953e5a4393cd40cbb3a244677
 size 3500316627