TheBloke
/

Qwen-7B-Chat-GPTQ

Text Generation

4-bit precision

Model card Files Files and versions

TheBloke commited on Nov 21, 2023

Commit

7e5e390

·

1 Parent(s): 0f4f61a

Fix config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -8,9 +8,9 @@
         "AutoConfig": "configuration_qwen.QWenConfig",
         "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
     },
-    "bf16": true,
     "emb_dropout_prob": 0.0,
-    "fp16": false,
     "fp32": false,
     "hidden_size": 4096,
     "initializer_range": 0.02,
@@ -64,7 +64,7 @@
     "use_cache_kernel": false,
     "use_cache_quantization": false,
     "use_dynamic_ntk": true,
-    "use_flash_attn": true,
     "use_logn_attn": true,
     "vocab_size": 151936
 }

         "AutoConfig": "configuration_qwen.QWenConfig",
         "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
     },
+    "bf16": false,
     "emb_dropout_prob": 0.0,
+    "fp16": true,
     "fp32": false,
     "hidden_size": 4096,
     "initializer_range": 0.02,
     "use_cache_kernel": false,
     "use_cache_quantization": false,
     "use_dynamic_ntk": true,
+    "use_flash_attn": "auto",
     "use_logn_attn": true,
     "vocab_size": 151936
 }