Upload folder using huggingface_hub

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "Qwen-14B-8bit-wikitext-ex512-len4096-hf-safetensors",
+  "_name_or_path": "Qwen/Qwen-14B",
   "architectures": [
     "QWenLMHeadModel"
   ],
   "attn_dropout_prob": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_qwen.QWenConfig",
-    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
+    "AutoConfig": "Qwen/Qwen-14B--configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "Qwen/Qwen-14B--modeling_qwen.QWenLMHeadModel"
   },
-  "bf16": false,
+  "bf16": true,
   "emb_dropout_prob": 0.0,
-  "fp16": true,
+  "fp16": false,
   "fp32": false,
   "hidden_size": 5120,
   "initializer_range": 0.02,
@@ -23,24 +23,6 @@
   "num_attention_heads": 40,
   "num_hidden_layers": 40,
   "onnx_safe": null,
-  "quantization_config": {
-    "batch_size": 1,
-    "bits": 8,
-    "block_name_to_quantize": null,
-    "damp_percent": 0.01,
-    "dataset": null,
-    "desc_act": false,
-    "disable_exllama": false,
-    "group_size": 128,
-    "model_seqlen": null,
-    "module_name_preceding_first_block": null,
-    "pad_token_id": null,
-    "quant_method": "gptq",
-    "sym": true,
-    "tokenizer": null,
-    "true_sequential": true,
-    "use_cuda_fp16": false
-  },
   "rotary_emb_base": 10000,
   "rotary_pct": 1.0,
   "scale_attn_weights": true,

pytorch_model.bin.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afc0c3a654a71e011f81456fd41107af811a60038e05db07c29a9a67e0cd455
+size 16029578416

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 8,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": "pytorch_model.bin"
+}