Update README.md

README.md

@@ -137,14 +137,14 @@ question = 'Hello, who are you?'
 response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
 print(f'User: {question}         Assistant: {response}')
 
-# single-image single-round conversation
-question = '<image>         Please describe the image shortly.'
-response = model.chat(tokenizer, pixel_values, question, generation_config, num_image_token=256)
+# text-image conversation
+question = '<image>         Please describe the image.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
 print(f'User: {question}         Assistant: {response}')
 
-# single-image multi-round conversation
-question = '<image>         Please describe the image in detail.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_image_token=256, history=None, return_history=True)
+# multi-round conversation
+question = 'What is best title for the image?'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
 print(f'User: {question}         Assistant: {response}')
 
 ```
@@ -153,7 +153,7 @@ print(f'User: {question}         Assistant: {response}')
 
 | Benchmark | Qwen2.5-VL-3B | InternVL2.5-4B | Ristretto-3B |
 | :-------: | :----------: | :-------------: | :----: |
-| MMBench-TEST-avg      | 76.8 | 78.2 | 82.7 |
+| MMBench-TEST-avg      | 76.8 | 78.2 | - |
 | MMStar                | 56.3 | 58.7 | 62.6 |
 | MMMU-VAL              | 51.2 | 51.8 | 49.1 |
 | MathVista-mini-test   | 61.2 | 60.8 | 67.9 |
@@ -161,7 +161,7 @@ print(f'User: {question}         Assistant: {response}')
 | AI2D                  | 81.4 | 81.4 | 84.3 |
 | OCRBench              | 82.8 | 82.0 | 84.0 | 
 | MMVet                 | 60.0 | 61.5 | 61.8 |
-| Average               | 64.5 | 65.1 | 67.8 |
+| Average               | 64.5 | 65.1 | - |
 
 We use [VLMEvalKit](https://github.com/open-compass/VLMEvalKit) to evaluate Ristretto-3B. Other results are taken from [OpenCompass](https://rank.opencompass.org.cn/leaderboard-multimodal)