Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-7b-hf",
+  "_name_or_path": "lmsys/vicuna-7b-v1.5-16k",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -10,6 +10,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 4096,
+  "max_sequence_length": 16384,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -17,7 +18,10 @@
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.31.0",

generation_config.json

@@ -1,8 +1,8 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 32000,
+  "max_length": 16384,
+  "pad_token_id": 0,
   "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:a0b01562bc48f2181e8e86828d05b2eb2e26e2d6ef26c0227cf17f7929ffae2c
+oid sha256:c46d2a0e26b397263cabd2b9ff7047965213ce33797b8518681515675c132106
 size 9976638373

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d88745942c57d4e1554f466a28e2515d0b43c7846d9e8df6ee3269e3160a3e
+oid sha256:6d7f4164e443e59f5043742ce41d27696a356b0052424067e9be365ba9b2df9f
 size 3500317102