GitHub / argilla-io/notus issues and pull requests
#14 - 【question】are you planning to support multi language model?
Issue -
State: open - Opened by Yongtae723 over 1 year ago
#13 - feat: add .ipynb for adding and updating models to `ollama`
Pull Request -
State: open - Opened by davidberenstein1957 over 1 year ago
- 1 comment
#12 - Run DPO step with multibinarized dataset
Issue -
State: closed - Opened by dvsrepo over 1 year ago
- 1 comment
Labels: experiments
#11 - Add Notus logo with Argilla watermark
Pull Request -
State: closed - Opened by alvarobartt almost 2 years ago
Labels: documentation
#10 - Warn about data contamination of UltraFeedback and add Notus naming explanation
Pull Request -
State: closed - Opened by alvarobartt almost 2 years ago
Labels: documentation
#9 - Major cleanup before release
Pull Request -
State: closed - Opened by alvarobartt almost 2 years ago
Labels: documentation
#8 - Adapt SFT fine-tuning script and configuration
Pull Request -
State: closed - Opened by alvarobartt almost 2 years ago
- 1 comment
Labels: experiments
#7 - Curate UltraFeedack dataset's overall_score
Issue -
State: open - Opened by dvsrepo almost 2 years ago
- 3 comments
Labels: team: ml
#6 - Add Intel Habana instructions and AlpacaEval results
Pull Request -
State: closed - Opened by gabrielmbmb almost 2 years ago
Labels: evaluation, intel
#5 - Run SFT step with the rating binarized data chosen responses
Issue -
State: closed - Opened by dvsrepo almost 2 years ago
- 1 comment
Labels: experiments
#3 - Run `EleutherAI/lm-eval-harness` and upload results
Pull Request -
State: closed - Opened by alvarobartt almost 2 years ago
Labels: evaluation
#2 - More experiments (full fine-tuning on 8 x A100 40GB)
Pull Request -
State: closed - Opened by alvarobartt almost 2 years ago
- 1 comment
Labels: experiments
#1 - Evaluate using MT-Bench and AlpacaEval to compare with Zephyr 7B Beta
Issue -
State: closed - Opened by alvarobartt almost 2 years ago
Labels: evaluation