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"
   ],
@@ -9,15 +9,18 @@
   "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,
-  "rms_norm_eps": 1e-06,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.30.2",
+  "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,
-  "transformers_version": "4.30.2"
+  "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 sha256:26ae433343db675e8bbdc3f6dbe7e536f8e4b07faa89ed32c1c6ffea5fe355d7
-size 9976637886
+oid sha256:3e096679efda6283fb179576664b7944f9444ae15cc2a3773471c7280e740ca2
+size 9976637950

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb72f857e168c66cba4502b7a53bb5a797d5ba543ea1498dc9f538f90f626f47
+oid sha256:2df35ab91b401d712bfd31e0e3b155d7146fbd30fbf849b83eabeb428788a6a6
 size 3500316627