Spaces:
Running
on
Zero
Running
on
Zero
Commit
·
80524d9
1
Parent(s):
41a0b93
fix bugs
Browse files
app.py
CHANGED
@@ -29,7 +29,7 @@ CAPTION_PROMPT = "Question: {}\nPlease describe the image. DO NOT try to answer
|
|
29 |
LLM_PROMPT = """In the following text, you will receive a detailed caption of an image and a relevant question. In addition, you will be provided with a tentative model response. You goal is to answer the question using these information.\n\n### The detailed caption of the provided image: {}\n\n### Note that the caption might contain incorrect solutions, do not be misguided by them.\n\n### A problem to be solved: {}\n\n### A tentative model response: {}\n\n### Note that the above tentative response might be inaccurate (due to calculation errors, incorrect logic/reasoning and so on), under such a case, please ignore it and give your own solutions. However, if you do not have enough evidence to show it is wrong, please output the tentative response."""
|
30 |
|
31 |
# === Initialize Models ===
|
32 |
-
MLLM_MODEL_PATH = "
|
33 |
LLM_MODEL_PATH = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
|
34 |
|
35 |
processor = AutoProcessor.from_pretrained(MLLM_MODEL_PATH)
|
|
|
29 |
LLM_PROMPT = """In the following text, you will receive a detailed caption of an image and a relevant question. In addition, you will be provided with a tentative model response. You goal is to answer the question using these information.\n\n### The detailed caption of the provided image: {}\n\n### Note that the caption might contain incorrect solutions, do not be misguided by them.\n\n### A problem to be solved: {}\n\n### A tentative model response: {}\n\n### Note that the above tentative response might be inaccurate (due to calculation errors, incorrect logic/reasoning and so on), under such a case, please ignore it and give your own solutions. However, if you do not have enough evidence to show it is wrong, please output the tentative response."""
|
30 |
|
31 |
# === Initialize Models ===
|
32 |
+
MLLM_MODEL_PATH = "KaiChen1998/RACRO-7B-CRO-GRPO"
|
33 |
LLM_MODEL_PATH = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
|
34 |
|
35 |
processor = AutoProcessor.from_pretrained(MLLM_MODEL_PATH)
|