Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / huggingface/open-r1 issues and pull requests
#92 - Improve repoduction of r1 reported score
Pull Request -
State: open - Opened by hynky1999 10 days ago
#91 - Change conda for uv
Pull Request -
State: open - Opened by andimarafioti 10 days ago
#89 - evaluate code for livecodebench, GPQA and Codeforces
Issue -
State: open - Opened by liyunsheng13 10 days ago
#88 - As the inference on local device is unaffordable for most people.
Issue -
State: open - Opened by PoTaTo-Mika 10 days ago
- 2 comments
#87 - Solution for Potential Inflation of Reward Metrics for Unparseable Go…
Pull Request -
State: open - Opened by agulati18 10 days ago
#87 - Solution for Potential Inflation of Reward Metrics for Unparseable Go…
Pull Request -
State: open - Opened by agulati18 10 days ago
#86 - Issue: Potential Inflation of Reward Metrics for Unparseable Gold Solutions
Issue -
State: open - Opened by agulati18 10 days ago
#86 - Issue: Potential Inflation of Reward Metrics for Unparseable Gold Solutions
Issue -
State: open - Opened by agulati18 10 days ago
#85 - tokenizer.chat_template is not set and no template argument was passed
Issue -
State: open - Opened by keeeeenw 10 days ago
#85 - tokenizer.chat_template is not set and no template argument was passed
Issue -
State: open - Opened by keeeeenw 10 days ago
#83 - Why the average power usage of GRPO training is at 50%?
Issue -
State: open - Opened by saidineshpola 10 days ago
#83 - Why the average power usage of GRPO training is at 50%?
Issue -
State: open - Opened by saidineshpola 10 days ago
#82 - deepseek-hack-map:: v3&r1
Issue -
State: open - Opened by ziwang-com 10 days ago
#82 - deepseek-hack-map:: v3&r1
Issue -
State: open - Opened by ziwang-com 10 days ago
#81 - pip install -e '.[dev]' hangs indefinitely (hours so far) on lighteval
Issue -
State: closed - Opened by axelmagn 10 days ago
- 1 comment
#81 - pip install -e '.[dev]' hangs indefinitely (hours so far) on lighteval
Issue -
State: closed - Opened by axelmagn 10 days ago
- 1 comment
#78 - feat: Added reward model according to paper.
Pull Request -
State: open - Opened by ahmeterdempmk 10 days ago
#78 - feat: Added reward model according to paper.
Pull Request -
State: open - Opened by ahmeterdempmk 10 days ago
#77 - Add recipe configs to optimize scripts (#73)
Pull Request -
State: open - Opened by LoserCheems 11 days ago
#77 - Add recipe configs to optimize scripts (#73)
Pull Request -
State: open - Opened by LoserCheems 11 days ago
#76 - Bump actions/checkout from 2 to 4
Pull Request -
State: closed - Opened by dependabot[bot] 11 days ago
Labels: dependencies, github_actions
#76 - Bump actions/checkout from 2 to 4
Pull Request -
State: closed - Opened by dependabot[bot] 11 days ago
Labels: dependencies, github_actions
#75 - Bump actions/setup-python from 2 to 5
Pull Request -
State: closed - Opened by dependabot[bot] 11 days ago
Labels: dependencies, github_actions
#75 - Bump actions/setup-python from 2 to 5
Pull Request -
State: closed - Opened by dependabot[bot] 11 days ago
Labels: dependencies, github_actions
#74 - Create new.py
Pull Request -
State: closed - Opened by Shouvik703 11 days ago
- 1 comment
#74 - Create new.py
Pull Request -
State: closed - Opened by Shouvik703 11 days ago
- 1 comment
#73 - Add recipe configs to optimize SFT scripts
Issue -
State: open - Opened by LoserCheems 11 days ago
#73 - Add recipe configs to optimize SFT scripts
Issue -
State: open - Opened by LoserCheems 11 days ago
#72 - Contributions in README.md
Pull Request -
State: closed - Opened by qgallouedec 11 days ago
#72 - Contributions in README.md
Pull Request -
State: closed - Opened by qgallouedec 11 days ago
#71 - Add `--input-batch-size`, `--client-replicas` args and download Ray logs
Pull Request -
State: closed - Opened by gabrielmbmb 11 days ago
#71 - Add `--input-batch-size`, `--client-replicas` args and download Ray logs
Pull Request -
State: closed - Opened by gabrielmbmb 11 days ago
#70 - Added dependabot integration for Python and GitHub Actions
Pull Request -
State: closed - Opened by ygdrax 11 days ago
- 2 comments
#70 - Added dependabot integration for Python and GitHub Actions
Pull Request -
State: closed - Opened by ygdrax 11 days ago
- 2 comments
#69 - ValueError: please provide at least one prompt
Issue -
State: open - Opened by fe1ixxu 11 days ago
- 5 comments
#69 - ValueError: please provide at least one prompt
Issue -
State: open - Opened by fe1ixxu 11 days ago
- 5 comments
#68 - FP8 training
Issue -
State: open - Opened by showgood163 11 days ago
#68 - FP8 training
Issue -
State: open - Opened by showgood163 11 days ago
#67 - No GRPOTrainer Group-Based Advantage Normalisation (Paper Eq. 3)
Issue -
State: closed - Opened by agulati18 11 days ago
#67 - No GRPOTrainer Group-Based Advantage Normalisation (Paper Eq. 3)
Issue -
State: closed - Opened by agulati18 11 days ago
#66 - Adding GRPOTrainer Group-Based Advantage Normalisation (Paper Eq. 3)
Pull Request -
State: closed - Opened by agulati18 11 days ago
- 2 comments
#66 - Adding GRPOTrainer Group-Based Advantage Normalisation (Paper Eq. 3)
Pull Request -
State: closed - Opened by agulati18 11 days ago
- 2 comments
#65 - We Need a Better Training Pipeline: GRPO Trainer Struggles with Long Completion Lengths on H100x8
Issue -
State: open - Opened by SeungyounShin 11 days ago
- 2 comments
#65 - We Need a Better Training Pipeline: GRPO Trainer Struggles with Long Completion Lengths on H100x8
Issue -
State: open - Opened by SeungyounShin 11 days ago
- 2 comments
#64 - Could you provide the model trained by GRPO?
Issue -
State: open - Opened by Ethereal-sakura 11 days ago
#64 - Could you provide the model trained by GRPO?
Issue -
State: open - Opened by Ethereal-sakura 11 days ago
#62 - docs: fix grammar and phrasing issues (1, 2, 3)
Pull Request -
State: closed - Opened by CharlesCNorton 11 days ago
#62 - docs: fix grammar and phrasing issues (1, 2, 3)
Pull Request -
State: closed - Opened by CharlesCNorton 11 days ago
#61 - Datasets for fine arts
Issue -
State: open - Opened by erkinalp 11 days ago
- 1 comment
#61 - Datasets for fine arts
Issue -
State: open - Opened by erkinalp 11 days ago
- 1 comment
#60 - Datasets for linguistics
Issue -
State: open - Opened by erkinalp 11 days ago
- 1 comment
#60 - Datasets for linguistics
Issue -
State: open - Opened by erkinalp 11 days ago
- 1 comment
#59 - What are expected training speed in GRPO
Issue -
State: open - Opened by whitead 11 days ago
- 3 comments
#59 - What are expected training speed in GRPO
Issue -
State: open - Opened by whitead 11 days ago
- 3 comments
#56 - How to supervise non-math data?
Issue -
State: open - Opened by Luodian 11 days ago
- 4 comments
#56 - How to supervise non-math data?
Issue -
State: open - Opened by Luodian 11 days ago
- 4 comments
#55 - Reward verification and evaluation fixes
Pull Request -
State: closed - Opened by hynky1999 12 days ago
- 1 comment
#55 - Reward verification and evaluation fixes
Pull Request -
State: closed - Opened by hynky1999 12 days ago
- 1 comment
#55 - Reward verification and evaluation fixes
Pull Request -
State: closed - Opened by hynky1999 12 days ago
- 1 comment
#55 - Reward verification and evaluation fixes
Pull Request -
State: closed - Opened by hynky1999 12 days ago
- 1 comment
#54 - docs: update README.md
Pull Request -
State: closed - Opened by eltociear 12 days ago
#54 - docs: update README.md
Pull Request -
State: closed - Opened by eltociear 12 days ago
#53 - Plan of attack uses R1 Zero for supervised fine-tuning in step 3.
Issue -
State: open - Opened by keskival 12 days ago
- 1 comment
#53 - Plan of attack uses R1 Zero for supervised fine-tuning in step 3.
Issue -
State: open - Opened by keskival 12 days ago
- 1 comment
#52 - Add Environment Test Script
Pull Request -
State: open - Opened by sambhavnoobcoder 12 days ago
- 4 comments
#52 - Add Environment Test Script
Pull Request -
State: open - Opened by sambhavnoobcoder 12 days ago
- 4 comments
#51 - Make HuggingFaceH4/aime_2024 public
Issue -
State: closed - Opened by mlabonne 12 days ago
- 3 comments
#51 - Make HuggingFaceH4/aime_2024 public
Issue -
State: closed - Opened by mlabonne 12 days ago
- 3 comments
#50 - Datasets for law
Issue -
State: open - Opened by erkinalp 12 days ago
- 3 comments
#50 - Datasets for law
Issue -
State: open - Opened by erkinalp 12 days ago
- 3 comments
#48 - [Willing to Contribute] Integrate SGLang into open-r1
Issue -
State: open - Opened by zhaochenyang20 12 days ago
#48 - [Willing to Contribute] Integrate SGLang into open-r1
Issue -
State: open - Opened by zhaochenyang20 12 days ago
#47 - Crazy VRAM usage with longer prompts
Issue -
State: open - Opened by andyl98 12 days ago
- 13 comments
#47 - Crazy VRAM usage with longer prompts
Issue -
State: open - Opened by andyl98 12 days ago
- 13 comments
#46 - how to train on MultiNode MultiGPU
Issue -
State: open - Opened by yuepengs 12 days ago
#46 - how to train on MultiNode MultiGPU
Issue -
State: open - Opened by yuepengs 12 days ago
#45 - Wondering why no format reward?
Issue -
State: open - Opened by Luodian 12 days ago
- 1 comment
#45 - Wondering why no format reward?
Issue -
State: open - Opened by Luodian 12 days ago
- 1 comment
#44 - 能否支持NPU?
Issue -
State: closed - Opened by laozhuang727 12 days ago
- 2 comments
#44 - 能否支持NPU?
Issue -
State: closed - Opened by laozhuang727 12 days ago
- 2 comments
#43 - vllm speed tweaks
Pull Request -
State: closed - Opened by anton-l 12 days ago
#43 - vllm speed tweaks
Pull Request -
State: closed - Opened by anton-l 12 days ago
#41 - Implement make evaluate command
Pull Request -
State: closed - Opened by mariagrandury 12 days ago
- 1 comment
#41 - Implement make evaluate command
Pull Request -
State: closed - Opened by mariagrandury 12 days ago
- 1 comment
#40 - Fix typos
Pull Request -
State: open - Opened by mariagrandury 12 days ago
- 1 comment
#40 - Fix typos
Pull Request -
State: open - Opened by mariagrandury 12 days ago
- 1 comment
#35 - what about open-v3?
Issue -
State: open - Opened by ehartford 12 days ago
- 1 comment
#35 - what about open-v3?
Issue -
State: open - Opened by ehartford 12 days ago
- 1 comment
#34 - Function calling at thinking time
Issue -
State: open - Opened by Kreijstal 12 days ago
- 4 comments
#34 - Function calling at thinking time
Issue -
State: open - Opened by Kreijstal 12 days ago
- 4 comments
#33 - Add devcontainer configuration for VS Code
Pull Request -
State: open - Opened by bhack 12 days ago
#33 - Add devcontainer configuration for VS Code
Pull Request -
State: open - Opened by bhack 12 days ago
#33 - Add devcontainer configuration for VS Code
Pull Request -
State: open - Opened by bhack 12 days ago
#33 - Add devcontainer configuration for VS Code
Pull Request -
State: open - Opened by bhack 12 days ago
#32 - let's create a discussion board on github to avoid issues for feature requests or sprawl?
Issue -
State: closed - Opened by russellballestrini 12 days ago
- 2 comments
#32 - let's create a discussion board on github to avoid issues for feature requests or sprawl?
Issue -
State: closed - Opened by russellballestrini 12 days ago
- 2 comments
#31 - Datasets for Medicine
Issue -
State: open - Opened by cyrilzakka 12 days ago
- 4 comments
#30 - chore: update trl to grpo_vllm branch, move lighteval to uv
Pull Request -
State: open - Opened by gerred 12 days ago
- 4 comments
#29 - Add example of generating data with deepseek r1 and distilled models
Pull Request -
State: closed - Opened by plaguss 12 days ago
#29 - Add example of generating data with deepseek r1 and distilled models
Pull Request -
State: closed - Opened by plaguss 12 days ago