Skip to content

Internvl series models update #1426

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.

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

Merged
merged 24 commits into from
Jul 18, 2024
Merged

Internvl series models update #1426

merged 24 commits into from
Jul 18, 2024

Conversation

hjh0119
Copy link
Collaborator

@hjh0119 hjh0119 commented Jul 17, 2024

PR type

  • Bug Fix
  • New Feature
  • Document Updates
  • More Models or Datasets Support

PR information

  • support model internvl2-1b and internvl2-llama3-76b
  • fix internvl2-4b template
  • support plain text dataset training for internvl series models
  • remove deprecated args in dpotrainer

Experiment results

test: training Internvl2-2B model for self-cognition dataset and custom image dataset

@hjh0119 hjh0119 changed the title Itvl Internvl series models update Jul 17, 2024
@hjh0119 hjh0119 merged commit e95db47 into modelscope:main Jul 18, 2024
1 of 2 checks passed
@hjh0119 hjh0119 deleted the itvl branch July 18, 2024 03:45
tastelikefeet added a commit to tastelikefeet/swift that referenced this pull request Jul 18, 2024
…alore

* commit '70b58b4155e956101b4f94cf344378e47f07fadf':
  Fix llava-hf (modelscope#1439)
  Fix bug and make lazydataset more stable (modelscope#1438)
  fix internvl2 template (modelscope#1436)
  Internvl series models update (modelscope#1426)
  fix internvl2 docs (modelscope#1433)

# Conflicts:
#	swift/llm/utils/model.py
hjh0119 added a commit to hjh0119/swift that referenced this pull request Jul 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants