Upload folder using huggingface_hub

README.md

@@ -17,6 +17,8 @@ base_model_relation: quantized
 Base model: [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507)
 
 <i>This model is quantized to 4-bit with a group size of 128.</i>
+<br>
+<i>Compared to earlier quantized versions, the new quantized model demonstrates better tokens/s efficiency. This improvement comes from setting desc_act=False in the quantization configuration.</i>
 
 ```
 vllm serve JunHowie/Qwen3-4B-Thinking-2507-GPTQ-Int4 
@@ -261,4 +263,4 @@ If you find our work helpful, feel free to give us a cite.
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2505.09388}, 
 }
-```
+```

config.json

@@ -58,7 +58,7 @@
   "quantization_config": {
     "bits": 4,
     "checkpoint_format": "gptq",
-    "desc_act": true,
+    "desc_act": false,
     "group_size": 128,
     "hyb_act": false,
     "lm_head": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a9996ce410451bbbdb0038efc9cc882c14c7192ec9065020b3d194b9c42e91
+oid sha256:7fbf018a7cb2568b6ac95cbf54cf629e1ca8923a4722aad8211065f11226de5e
 size 2669888648

quantize_config.json

@@ -1,7 +1,7 @@
 {
   "bits": 4,
   "group_size": 128,
-  "desc_act": true,
+  "desc_act": false,
   "hyb_act": false,
   "sym": true,
   "lm_head": false,