Update README.md

README.md

@@ -99,25 +99,25 @@ from qwen_vl_utils import process_vision_info
 
 # default: Load the model on the available device(s)
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
+    "Qwen/Qwen2.5-VL-7B-Instruct-AWQ", torch_dtype="auto", device_map="auto"
 )
 
 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 # model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-#     "Qwen/Qwen2.5-VL-7B-Instruct",
+#     "Qwen/Qwen2.5-VL-7B-Instruct-AWQ",
 #     torch_dtype=torch.bfloat16,
 #     attn_implementation="flash_attention_2",
 #     device_map="auto",
 # )
 
 # default processer
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct-AWQ")
 
 # The default range for the number of visual tokens per image in the model is 4-16384.
 # You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
 # min_pixels = 256*28*28
 # max_pixels = 1280*28*28
-# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
+# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct-AWQ", min_pixels=min_pixels, max_pixels=max_pixels)
 
 messages = [
     {
@@ -207,7 +207,7 @@ The model supports a wide range of resolution inputs. By default, it uses the na
 min_pixels = 256 * 28 * 28
 max_pixels = 1280 * 28 * 28
 processor = AutoProcessor.from_pretrained(
-    "Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels
+    "Qwen/Qwen2.5-VL-7B-Instruct-AWQ", min_pixels=min_pixels, max_pixels=max_pixels
 )
 ```
 
@@ -274,6 +274,26 @@ However, it should be noted that this method has a significant impact on the per
 At the same time, for long video inputs, since MRoPE itself is more economical with ids, the max_position_embeddings can be directly modified to a larger value, such as 64k.
 
 
+### Benchmark
+#### Performance of Quantized Models
+This section reports the generation performance of quantized models (including GPTQ and AWQ) of the Qwen2.5-VL series. Specifically, we report:
+
+- MMMU_VAL (Accuracy)
+- DocVQA_VAL (Accuracy)
+- MMBench_DEV_EN (Accuracy)
+- MathVista_MINI (Accuracy)
+
+We use [VLMEvalkit](https://github.com/open-compass/VLMEvalKit) to evaluate all models.
+
+| Model Size | Quantization | MMMU_VAL | DocVQA_VAL | MMBench_EDV_EN | MathVista_MINI  |
+| --- | --- | --- | --- | --- | --- |
+| Qwen2.5-VL-72B-Instruct | BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) | 70.0 | 96.1 | 88.2 | 75.3 |
+|  | AWQ<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct-AWQ)) | 69.1 | 96.0 | 87.9 | 73.8 |
+| Qwen2.5-VL-7B-Instruct | BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) | 58.4 | 94.9 | 84.1 | 67.9 |
+|  | AWQ<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct-AWQ)) | 55.6 | 94.6 | 84.2 | 64.7 |
+| Qwen2.5-VL-3B-Instruct | BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) | 51.7 | 93.0 | 79.8 | 61.4 |
+|  | AWQ<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct-AWQ)) | 49.1 | 91.8 | 78.0 | 58.8 |
+
 
 
 ## Citation