Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "_name_or_path": "elliotthwang/Chinese-LLaMa-GPTQ",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,7 +9,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.31.0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

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

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f44e7e2dcca7af42ce7bec88e48c7e863e3b89c413a35687259c03a49b4c019
+oid sha256:9081e66392934d3c86e701bddcee2db9eb5c87e95cb3c442c3cf1ef39f2c4017
 size 9976637886

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480670b7749e78b08ad9bd02767d2ed16b5020e7a5ab08a26aa06603bb7d2e84
+oid sha256:e454bc4760de12b0c5206ca62cd3eebaba0e59e1f52d767b36ce6bcbdfebc6f6
 size 3500316627