Add pipeline tag and library name

README.md

@@ -1,5 +1,6 @@
 ---
-license: mit
+base_model:
+- lmms-lab/llava-onevision-qwen2-7b-ov
 datasets:
 - CodeGoat24/HPD
 - CodeGoat24/LiFT-HRA
@@ -9,11 +10,11 @@ datasets:
 - CodeGoat24/VideoFeedback
 - CodeGoat24/LLaVA-Critic-113k
 - CodeGoat24/VideoDPO
-base_model:
-- lmms-lab/llava-onevision-qwen2-7b-ov
+license: mit
+pipeline_tag: image-text-to-text
+library_name: llava
 ---
 
-
 # Unified-Reward-7B
 
 ## Model Summary
@@ -64,12 +65,22 @@ image_tensor = [_image.to(dtype=torch.float16, device=device) for _image in imag
 conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
 
 # pairwise ranking
-critic_prompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of the answers provided by a Large Multimodal Model (LMM). Determine which answer is better and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe first response: [The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.]\nThe second response: [This is a handwritten number seven.]\nASSISTANT:\n"
+critic_prompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of the answers provided by a Large Multimodal Model (LMM). Determine which answer is better and explain your reasoning with specific details. Your task is provided as follows:
+Question: [What this image presents?]
+The first response: [The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.]
+The second response: [This is a handwritten number seven.]
+ASSISTANT:
+"
 
 # pointwise scoring
-# critic_prompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of answer answers provided by a Large Multimodal Model (LMM). Score the response out of 100 and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe LMM response: [This is a handwritten number seven.]\nASSISTANT:\n "
-
-question = DEFAULT_IMAGE_TOKEN + "\n" + critic_prompt
+# critic_prompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of answer answers provided by a Large Multimodal Model (LMM). Score the response out of 100 and explain your reasoning with specific details. Your task is provided as follows:
+Question: [What this image presents?]
+The LMM response: [This is a handwritten number seven.]
+ASSISTANT:
+ "
+
+question = DEFAULT_IMAGE_TOKEN + "
+" + critic_prompt
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], question)
 conv.append_message(conv.roles[1], None)