Skip to content

FEAT: Support new model CogVLM - #1551

Merged
qinxuye merged 7 commits into
xorbitsai:mainfrom
amumu96:cogvlm
May 31, 2024
Merged

FEAT: Support new model CogVLM#1551
qinxuye merged 7 commits into
xorbitsai:mainfrom
amumu96:cogvlm

Conversation

@amumu96

@amumu96 amumu96 commented May 29, 2024

Copy link
Copy Markdown
Contributor
image

@XprobeBot XprobeBot added this to the v0.11.3 milestone May 29, 2024
Comment thread xinference/model/llm/pytorch/cogvlm2.py Outdated
@qinxuye qinxuye changed the title FNH: Support new model CogVLM FEAT: Support new model CogVLM May 30, 2024
wuzhaoxin added 3 commits May 31, 2024 02:15
# Conflicts:
#	xinference/model/llm/llm_family.json

@qinxuye qinxuye left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

LGTM

@qinxuye
qinxuye merged commit f8dd5ba into xorbitsai:main May 31, 2024
@amumu96
amumu96 deleted the cogvlm branch June 3, 2024 04:15
@fire17

fire17 commented Jan 8, 2025

Copy link
Copy Markdown

can you guys add CogVLM2 to the BrillAI platform?
I want to test its pixel coordinate functionality - ie
return the location of the button named "retry" in [[x0,y0,x1,y1]] format
it should return the bounding box in values between 1-1000 in reference to the image,
locating / pinpointing vlm is not something i have seen yet but cogvlm2 seems to be able to do this
Thanks :) and all the best

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants