Skip to content

fix bug #7309 deepseek-ai/deepseek-vl2 model can not be select as a VL model to parse pdf image #7312

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

fix bug #7309 deepseek-ai/deepseek-vl2 model can not be select as a VL model to parse pdf image #7312

Changes from 5 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
0f816ba
fix bug #6990 internal server error ehile chunking:expected string or…
Apr 17, 2025
d9ceb45
Merge branch 'infiniflow:main' into main
QuintinTao Apr 25, 2025
3bedee8
Merge branch 'infiniflow:main' into main
QuintinTao Apr 25, 2025
e6db141
Merge branch 'infiniflow:main' into main
QuintinTao Apr 25, 2025
cf98165
fix #7309
Apr 25, 2025
bd0c8e5
Merge branch 'infiniflow:main' into main
QuintinTao May 1, 2025
9d16b87
fix #7309 and revise the code review
May 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 31 additions & 1 deletion conf/llm_factories.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2543,7 +2543,7 @@
"llm_name": "deepseek-ai/deepseek-vl2",
"tags": "LLM,CHAT,4k",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

tags should be LLM,IMAGE2TEXT,4k

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK.thanks

"max_tokens": 4096,
"model_type": "chat"
"model_type": "image2text"
},
{
"llm_name": "deepseek-ai/Janus-Pro-7B",
Expand All @@ -2557,6 +2557,36 @@
"max_tokens": 32768,
"model_type": "image2text"
},
{
"llm_name": "Qwen/Qwen2.5-VL-72B-Instruct",
"tags": "LLM,IMAGE2TEXT,128k",
"max_tokens": 131072,
"model_type": "image2text"
},
{
"llm_name": "Qwen/Qwen2.5-VL-32B-Instruct",
"tags": "LLM,IMAGE2TEXT,128k",
"max_tokens": 131072,
"model_type": "image2text"
},
{
"llm_name": "Pro/Qwen/Qwen2.5-VL-7B-Instruct",
"tags": "LLM,IMAGE2TEXT,128k",
"max_tokens": 131072,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

tags should be LLM,IMAGE2TEXT,32k
max_tokens should be 32768
image

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK. thanks

"model_type": "image2text"
},
{
"llm_name": "Qwen/Qwen2-VL-72B-Instruct",
"tags": "LLM,IMAGE2TEXT,32k",
"max_tokens": 32768,
"model_type": "image2text"
},
{
"llm_name": "Pro/Qwen/Qwen2-VL-7B-Instruct",
"tags": "LLM,IMAGE2TEXT,32k",
"max_tokens": 32768,
"model_type": "image2text"
},
{
"llm_name": "FunAudioLLM/CosyVoice2-0.5B",
"tags": "LLM,TTS,32k",
Expand Down