Skip to content

Issues: ai-hero/llm-research-fine-tuning

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

13 Open 4 Closed
13 Open 4 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Add RAG Fine-tuning
#35 opened Jan 4, 2024 by rparundekar
2
DPO
#34 opened Jan 4, 2024 by rparundekar
How does the loss / cost compare with other frameworks for the same dataset
#33 opened Jan 4, 2024 by rparundekar
LoRA is taking longer than SFT to train on A100s
#32 opened Jan 4, 2024 by rparundekar
Fix Mistral 7b issue
#31 opened Jan 4, 2024 by rparundekar
Create service using knative that scales to 0. Currently, the costs are crazy
#30 opened Dec 29, 2023 by rparundekar
Add tags for dataset name, version, config, and training params to W&B
#27 opened Dec 25, 2023 by rparundekar
Add eval logic based on https://txt.cohere.com/evaluating-llm-outputs/#llm-generated-evaluation
#26 opened Dec 25, 2023 by rparundekar
Investigate if max seq length affects quality?
#25 opened Dec 25, 2023 by rparundekar
Make test split eval work
#21 opened Dec 24, 2023 by rparundekar
Save the model with the best eval score.
#20 opened Dec 24, 2023 by rparundekar
Load base model from S3
#18 opened Dec 24, 2023 by rparundekar
Save both the model and tokenizer into S3
#17 opened Dec 24, 2023 by rparundekar
ProTip! Follow long discussions with comments:>50.