Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,7 +16,6 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float32",

generation_config.json

@@ -1,8 +1,10 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
+  "max_length": 4096,
   "pad_token_id": 0,
-  "transformers_version": "4.36.2",
-  "use_cache": false
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.36.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200e3bdc58c880cec8825a7f05ee687aea74a34e71a409ecaeb130fdfe0c2cdb
+oid sha256:4f7239480118e21de6a4fe55869885d518b3ba321d72371d2a9e6c842a5f883f
 size 4992587592

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba955bd58b27bd6967dddf805af92161b8791e584a76635fecee556368f0198
+oid sha256:94ae7bc01eaf58d737e4f35c95d3b2b75b2cb6df6b3ad6f142c3ccc077d707db
 size 2555349880