fix minor typo

scikkk · Jul 18, 2024 · c36135a · c36135a
1 parent 61eddb0
commit c36135a
Show file tree

Hide file tree

Showing 5 changed files with 6 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -93,7 +93,7 @@ VLMEvalKit will use a **judge LLM** to extract answer from the output if you set
 | [**LLaVA (XTuner)**](https://huggingface.co/xtuner/llava-internlm-7b)🚅 | [**CogVLM-[Chat/Llama3]**](https://huggingface.co/THUDM/cogvlm-chat-hf)🚅 | [**ShareCaptioner**](https://huggingface.co/spaces/Lin-Chen/Share-Captioner)🚅 | [**CogVLM-Grounding-Generalist**](https://huggingface.co/THUDM/cogvlm-grounding-generalist-hf)🚅 |
 | [**Monkey**](https://github.com/Yuliang-Liu/Monkey)🚅, [**Monkey-Chat**](https://github.com/Yuliang-Liu/Monkey)🚅 | [**EMU2-Chat**](https://github.com/baaivision/Emu)🚅🎞️         | [**Yi-VL-[6B/34B]**](https://huggingface.co/01-ai/Yi-VL-6B)  | [**MMAlaya**](https://huggingface.co/DataCanvas/MMAlaya)🚅    |
 | [**InternLM-XComposer-2.5**](https://github.com/InternLM/InternLM-XComposer)🚅🎞️ | [**MiniCPM-[V1/V2/V2.5]**](https://huggingface.co/openbmb/MiniCPM-V)🚅 | [**OmniLMM-12B**](https://huggingface.co/openbmb/OmniLMM-12B) | [**InternVL-Chat-[V1-1/V1-2/V1-5/V2]**](https://github.com/OpenGVLab/InternVL)🚅🎞️, <br>[**Mini-InternVL-Chat-[2B/4B]-V1-5**](https://github.com/OpenGVLab/InternVL)🚅🎞️ |
-| [**DeepSeek-VL**](https://github.com/deepseek-ai/DeepSeek-VL/tree/main)🎞️ | [**LLaVA-NeXT**](https://llava-vl.github.io/blog/2024-01-30-llava-next/)🚅 | [**Bunny-Llama3**](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V)🚅 | [**XVERSE-V-13B**](https://github.com/xverse-ai/XVERSE-V-13B/blob/main/vxverse/models/vxverse.py) |
+| [**DeepSeek-VL**](https://github.com/deepseek-ai/DeepSeek-VL/tree/main)🎞️ | [**LLaVA-NeXT**](https://llava-vl.github.io/blog/2024-01-30-llava-next/)🚅 | [**Bunny-Llama3**](https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V)🚅 | [**XVERSE-V-13B**](https://github.com/xverse-ai/XVERSE-V-13B/blob/main/vxverse/models/vxverse.py) |
 | [**PaliGemma-3B**](https://huggingface.co/google/paligemma-3b-pt-448) 🚅 | [**360VL-70B**](https://huggingface.co/qihoo360/360VL-70B) 🚅 | [**Phi-3-Vision**](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct)🚅 | [**WeMM**](https://github.com/scenarios/WeMM)🚅               |
 | [**GLM-4v-9B**](https://huggingface.co/THUDM/glm-4v-9b) 🚅    | [**Cambrian-[8B/13B/34B]**](https://cambrian-mllm.github.io/) |                                                              |                                                              |
 

diff --git a/docs/ja/README_ja.md b/docs/ja/README_ja.md
@@ -88,7 +88,7 @@ VLMEvalKitは、キーを設定すると**判定LLM**を使用して出力から
 | [**LLaVA (XTuner)**](https://huggingface.co/xtuner/llava-internlm-7b)🚅 | [**CogVLM-[Chat/Llama3]**](https://huggingface.co/THUDM/cogvlm-chat-hf)🚅 | [**ShareCaptioner**](https://huggingface.co/spaces/Lin-Chen/Share-Captioner)🚅 | [**CogVLM-Grounding-Generalist**](https://huggingface.co/THUDM/cogvlm-grounding-generalist-hf)🚅 |
 | [**Monkey**](https://github.com/Yuliang-Liu/Monkey)🚅, [**Monkey-Chat**](https://github.com/Yuliang-Liu/Monkey)🚅 | [**EMU2-Chat**](https://github.com/baaivision/Emu)🚅🎞️         | [**Yi-VL-[6B/34B]**](https://huggingface.co/01-ai/Yi-VL-6B)  | [**MMAlaya**](https://huggingface.co/DataCanvas/MMAlaya)🚅    |
 | [**InternLM-XComposer-2.5**](https://github.com/InternLM/InternLM-XComposer)🚅🎞️ | [**MiniCPM-[V1/V2/V2.5]**](https://huggingface.co/openbmb/MiniCPM-V)🚅 | [**OmniLMM-12B**](https://huggingface.co/openbmb/OmniLMM-12B) | [**InternVL-Chat-[V1-1/V1-2/V1-5/V2]**](https://github.com/OpenGVLab/InternVL)🚅🎞️, <br>[**Mini-InternVL-Chat-[2B/4B]-V1-5**](https://github.com/OpenGVLab/InternVL)🚅🎞️ |
-| [**DeepSeek-VL**](https://github.com/deepseek-ai/DeepSeek-VL/tree/main)🎞️ | [**LLaVA-NeXT**](https://llava-vl.github.io/blog/2024-01-30-llava-next/)🚅 | [**Bunny-Llama3**](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V)🚅 | [**XVERSE-V-13B**](https://github.com/xverse-ai/XVERSE-V-13B/blob/main/vxverse/models/vxverse.py) |
+| [**DeepSeek-VL**](https://github.com/deepseek-ai/DeepSeek-VL/tree/main)🎞️ | [**LLaVA-NeXT**](https://llava-vl.github.io/blog/2024-01-30-llava-next/)🚅 | [**Bunny-Llama3**](https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V)🚅 | [**XVERSE-V-13B**](https://github.com/xverse-ai/XVERSE-V-13B/blob/main/vxverse/models/vxverse.py) |
 | [**PaliGemma-3B**](https://huggingface.co/google/paligemma-3b-pt-448) 🚅 | [**360VL-70B**](https://huggingface.co/qihoo360/360VL-70B) 🚅 | [**Phi-3-Vision**](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct)🚅 | [**WeMM**](https://github.com/scenarios/WeMM)🚅               |
 | [**GLM-4v-9B**](https://huggingface.co/THUDM/glm-4v-9b) 🚅    | [**Cambrian-[8B/13B/34B]**](https://cambrian-mllm.github.io/) |                                                              |                                                              |
 

diff --git a/docs/zh-CN/README_zh-CN.md b/docs/zh-CN/README_zh-CN.md
@@ -98,7 +98,7 @@
 | [**LLaVA (XTuner)**](https://huggingface.co/xtuner/llava-internlm-7b)🚅 | [**CogVLM-[Chat/Llama3]**](https://huggingface.co/THUDM/cogvlm-chat-hf)🚅 | [**ShareCaptioner**](https://huggingface.co/spaces/Lin-Chen/Share-Captioner)🚅 | [**CogVLM-Grounding-Generalist**](https://huggingface.co/THUDM/cogvlm-grounding-generalist-hf)🚅 |
 | [**Monkey**](https://github.com/Yuliang-Liu/Monkey)🚅, [**Monkey-Chat**](https://github.com/Yuliang-Liu/Monkey)🚅 | [**EMU2-Chat**](https://github.com/baaivision/Emu)🚅🎞️         | [**Yi-VL-[6B/34B]**](https://huggingface.co/01-ai/Yi-VL-6B)  | [**MMAlaya**](https://huggingface.co/DataCanvas/MMAlaya)🚅    |
 | [**InternLM-XComposer-2.5**](https://github.com/InternLM/InternLM-XComposer)🚅🎞️ | [**MiniCPM-[V1/V2/V2.5]**](https://huggingface.co/openbmb/MiniCPM-V)🚅 | [**OmniLMM-12B**](https://huggingface.co/openbmb/OmniLMM-12B) | [**InternVL-Chat-[V1-1/V1-2/V1-5/V2]**](https://github.com/OpenGVLab/InternVL)🚅🎞️, <br>[**Mini-InternVL-Chat-[2B/4B]-V1-5**](https://github.com/OpenGVLab/InternVL)🚅🎞️ |
-| [**DeepSeek-VL**](https://github.com/deepseek-ai/DeepSeek-VL/tree/main)🎞️ | [**LLaVA-NeXT**](https://llava-vl.github.io/blog/2024-01-30-llava-next/)🚅 | [**Bunny-Llama3**](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V)🚅 | [**XVERSE-V-13B**](https://github.com/xverse-ai/XVERSE-V-13B/blob/main/vxverse/models/vxverse.py) |
+| [**DeepSeek-VL**](https://github.com/deepseek-ai/DeepSeek-VL/tree/main)🎞️ | [**LLaVA-NeXT**](https://llava-vl.github.io/blog/2024-01-30-llava-next/)🚅 | [**Bunny-Llama3**](https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V)🚅 | [**XVERSE-V-13B**](https://github.com/xverse-ai/XVERSE-V-13B/blob/main/vxverse/models/vxverse.py) |
 | [**PaliGemma-3B**](https://huggingface.co/google/paligemma-3b-pt-448) 🚅 | [**360VL-70B**](https://huggingface.co/qihoo360/360VL-70B) 🚅 | [**Phi-3-Vision**](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct)🚅 | [**WeMM**](https://github.com/scenarios/WeMM)🚅               |
 | [**GLM-4v-9B**](https://huggingface.co/THUDM/glm-4v-9b) 🚅    | [**Cambrian-[8B/13B/34B]**](https://cambrian-mllm.github.io/) |                                                              |                                                              |
 

diff --git a/vlmeval/api/sensechat_vision.py b/vlmeval/api/sensechat_vision.py
@@ -118,7 +118,7 @@ def build_prompt(self, line, dataset=None):
         elif dataset is not None and listinstr(['HallusionBench'], dataset):
             question = line['question']
             prompt = question + ' Please answer yes or no. Answer the question using a single word or phrase.'
-        elif dataset is not None and DATASET_TYPE(dataset) == 'multi-choice' and 'MMMU' not in dataset:
+        elif dataset is not None and DATASET_TYPE(dataset) == 'MCQ' and 'MMMU' not in dataset:
             prompt = self.build_multi_choice_prompt(line, dataset)
         elif dataset is not None and DATASET_TYPE(dataset) == 'VQA':
             if 'MathVista' in dataset:

diff --git a/vlmeval/vlm/cogvlm.py b/vlmeval/vlm/cogvlm.py
@@ -29,7 +29,7 @@ def __init__(self, model_path='THUDM/glm-4v-9b', **kwargs):
     def generate_inner(self, message, dataset=None):
         prompt, image_path = self.message_to_promptimg(message, dataset=dataset)
         image = Image.open(image_path).convert('RGB')
-        if dataset is not None and DATASET_TYPE(dataset) in ['multi-choice', 'Y/N']:
+        if dataset is not None and DATASET_TYPE(dataset) in ['MCQ', 'Y/N']:
             prompt += '\nShort Answer.'
         inputs = self.tokenizer.apply_chat_template(
             [{'role': 'user', 'image': image, 'content': prompt}],
@@ -110,7 +110,7 @@ def build_prompt(self, line, dataset=None):
 
     def generate_inner(self, message, dataset=None):
         prompt, image_path = self.message_to_promptimg(message, dataset=dataset)
-        if dataset is not None and DATASET_TYPE(dataset) in ['multi-choice', 'Y/N']:
+        if dataset is not None and DATASET_TYPE(dataset) in ['MCQ', 'Y/N']:
             prompt += '\nShort Answer.'
 
         image = Image.open(image_path).convert('RGB')