Skip to content
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

DeepseekVL add local_repo_path argument AND infer support delete truncation_strategy #883

Merged
merged 7 commits into from
May 11, 2024

Conversation

starxhong
Copy link
Contributor

PR type

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

PR information

1,DeepseekVL needs clone repo from github at runtime now. Whereas, in case of network unreached or some custom changes to DeepseekVL,a local repo may be need. 'local_repo_path' argument is added here.
2,Infer with input length exceeds the max_length will raise an ValueError now, which is NOT we usually expect. when truncation_strategy is 'delete',just return a empty repsonse seems more friendly.

Experiment results

Paste your experiment result here(if needed).

@hjh0119
Copy link
Collaborator

hjh0119 commented May 10, 2024

@starxhong thank you for your contribution!

Could you please run the code through a lint test?

@tastelikefeet tastelikefeet merged commit 550c694 into modelscope:main May 11, 2024
1 of 2 checks passed
tastelikefeet added a commit to tastelikefeet/swift that referenced this pull request May 14, 2024
* commit 'bdc8f54848daad335e513183482e16cc5da17c88': (36 commits)
  fix export self-cognition (modelscope#929)
  fix deepseek2(modelscope#924)
  Add 34b quantized model (modelscope#920)
  yi1.5 quantized model (modelscope#917)
  update readme&doc (modelscope#916)
  init (modelscope#915)
  fix unsloth import (modelscope#912)
  add more models local repo support (modelscope#911)
  lint
  DeepseekVL add local_repo_path argument AND infer support delete truncation_strategy (modelscope#883)
  Support Hqq and Eetq quantization  (modelscope#900)
  fix val_sample (modelscope#909)
  Add val_dataset argument (modelscope#906)
  Refactor sequence parallel (modelscope#823)
  replace dataset name with modelscope dataset id (modelscope#899)
  replace dataset name with dataset path from modelscope (modelscope#897)
  fix doc link
  enable longlora and adalora merge (modelscope#892)
  fix lisa show bug (modelscope#891)
  update doc (modelscope#888)
  ...

# Conflicts:
#	swift/llm/utils/dataset.py
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.

None yet

3 participants