Upload 3 files

config.json

@@ -8,10 +8,10 @@
     "AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
     "AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
   },
-  "bf16": true,
+  "bf16": false,
   "emb_dropout_prob": 0.0,
   "fp16": false,
-  "fp32": false,
+  "fp32": true,
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 22016,
@@ -29,8 +29,8 @@
     "desc_act": false,
     "group_size": 128,
     "is_marlin_format": false,
-    "model_file_base_name": "gptq_model-4bit-128g",
-    "model_name_or_path": "Qwen-7B-4bit",
+    "model_file_base_name": null,
+    "model_name_or_path": null,
     "quant_method": "gptq",
     "static_groups": false,
     "sym": true,
@@ -44,12 +44,12 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "QWenTokenizer",
   "torch_dtype": "float16",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.38.1",
   "use_cache": true,
   "use_cache_kernel": false,
   "use_cache_quantization": false,
   "use_dynamic_ntk": true,
-  "use_flash_attn": true,
+  "use_flash_attn": false,
   "use_logn_attn": true,
   "vocab_size": 151936
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2393b2d40537456cd8cd8cd876999c6ef834e4edc9346e8b7be6e4fa0769a90f
-size 5860862723
+oid sha256:d606b03c92a7744aa3d9dc082b393526ba13badc35cdb01e2b470a59ebfa882f
+size 8454625504

quantize_config.json

@@ -6,8 +6,8 @@
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "Qwen-7B-4bit",
-  "model_file_base_name": "gptq_model-4bit-128g",
+  "model_name_or_path": null,
+  "model_file_base_name": null,
   "is_marlin_format": false,
   "quant_method": "gptq"
 }