reyvan
/

Qwen-7B-4bit2

Text Generation

4-bit precision

Model card Files Files and versions Community

reyvan commited on Feb 26

Commit

9e027c7

•

1 Parent(s): 82daa44

Upload 3 files

Files changed (2) hide show

config.json +4 -4
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -8,10 +8,10 @@
     "AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
     "AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
   },
-  "bf16": false,
   "emb_dropout_prob": 0.0,
   "fp16": false,
-  "fp32": true,
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 22016,
@@ -44,12 +44,12 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "QWenTokenizer",
   "torch_dtype": "float16",
-  "transformers_version": "4.38.1",
   "use_cache": true,
   "use_cache_kernel": false,
   "use_cache_quantization": false,
   "use_dynamic_ntk": true,
-  "use_flash_attn": false,
   "use_logn_attn": true,
   "vocab_size": 151936
 }

     "AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
     "AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
   },
+  "bf16": true,
   "emb_dropout_prob": 0.0,
   "fp16": false,
+  "fp32": false,
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 22016,
   "tie_word_embeddings": false,
   "tokenizer_class": "QWenTokenizer",
   "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "use_cache_kernel": false,
   "use_cache_quantization": false,
   "use_dynamic_ntk": true,
+  "use_flash_attn": true,
   "use_logn_attn": true,
   "vocab_size": 151936
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d606b03c92a7744aa3d9dc082b393526ba13badc35cdb01e2b470a59ebfa882f
-size 8454625504

 version https://git-lfs.github.com/spec/v1
+oid sha256:52c15f9dd0ec4a8ca88abdf141d3bc9382c9777d11673762fa85553c312c7c50
+size 5860862252