Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / tatsu-lab/alpaca_farm issues and pull requests
#33 - Can you provide another graph of reward model over-optimization in Figure.5 of the paper?
Issue -
State: closed - Opened by twidddj over 1 year ago
- 1 comment
#32 - Differences in results between the paper and the code
Issue -
State: closed - Opened by idanshen over 1 year ago
- 1 comment
#31 - [Reward Model Training] Inconsistent accuracy caused by flash-attention
Issue -
State: closed - Opened by nbl97 over 1 year ago
- 1 comment
#31 - [Reward Model Training] Inconsistent accuracy caused by flash-attention
Issue -
State: closed - Opened by nbl97 over 1 year ago
- 1 comment
#30 - Where is auto_annotations/annotators/annotator_pool_v0/configs.yaml ?
Issue -
State: closed - Opened by HaSai666 over 1 year ago
- 1 comment
#30 - Where is auto_annotations/annotators/annotator_pool_v0/configs.yaml ?
Issue -
State: closed - Opened by HaSai666 over 1 year ago
- 1 comment
#29 - Update README.md
Pull Request -
State: closed - Opened by eltociear over 1 year ago
- 1 comment
#29 - Update README.md
Pull Request -
State: closed - Opened by eltociear over 1 year ago
- 1 comment
#28 - recover_model_weight on reward-sim meet problem of _name_or_path and backbone_model_name_or_path
Issue -
State: closed - Opened by REIGN12 over 1 year ago
- 3 comments
#28 - recover_model_weight on reward-sim meet problem of _name_or_path and backbone_model_name_or_path
Issue -
State: closed - Opened by REIGN12 over 1 year ago
- 3 comments
#27 - [ENH] release main model checkpoints
Pull Request -
State: closed - Opened by rtaori over 1 year ago
#27 - [ENH] release main model checkpoints
Pull Request -
State: closed - Opened by rtaori over 1 year ago
#26 - [ENH] alpaca_leaderboard from JSON
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#25 - Clean up all commits.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#24 - update readme
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#24 - update readme
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#23 - update readme
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#23 - update readme
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#22 - Yann clean eval
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#22 - Yann clean eval
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#21 - fix tokenizer issue that needs protobuf downgrade.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#20 - clean up bon and README
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#20 - clean up bon and README
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#19 - WIP readme
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#19 - WIP readme
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
#18 - fix len arguments.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#18 - fix len arguments.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#17 - Read
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#17 - Read
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#16 - patch license.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#13 - refactor optimizer creation.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#12 - PPO prep
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#11 - fix bug in data processing and make nice
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#10 - remove flash gpt2.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#9 - fix bugs in best of n
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#8 - complete best of n
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#7 - fix decode.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#6 - [ENH] auto annotators
Pull Request -
State: closed - Opened by YannDubs over 1 year ago
- 2 comments
#5 - simplify.
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#3 - finalize reward modeling
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#2 - Reward
Pull Request -
State: closed - Opened by lxuechen over 1 year ago
#1 - Reward
Pull Request -
State: closed - Opened by lxuechen over 1 year ago