Skip to content

Pull requests: jingyaogong/minimind

New pull request New
31 Open 82 Closed
31 Open 82 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

docs: 完善中英双语数据集指南 / expand bilingual dataset guide
#833 opened Sep 1, 2026 by AmIrRX0 Loading…
fix: 修复多语言重复惩罚 / make repetition penalty multilingual
#832 opened Sep 1, 2026 by AmIrRX0 Loading…
1
docs: 添加多语言 README 入口 / add multilingual README entry points
#831 opened Sep 1, 2026 by AmIrRX0 Loading…
[fix] keep DPO preference-pair think formatting aligned
#829 opened Aug 30, 2026 by DaoyuanLi2816 Loading…
chore: remove .idea and add to .gitignore
#825 opened Aug 27, 2026 by Jarrily Loading…
[refactor] remove redundant rollout update_policy after torch.compile
#821 opened Aug 24, 2026 by lycDragonSlayer Loading…
1
[feat] add MPS support for Apple Silicon
#818 opened Aug 13, 2026 by ctrl-alt-del Loading…
Add CE regularization term to DPO loss
#817 opened Aug 12, 2026 by QZL-max Loading…
feat: 增加通用 On-Policy Distillation（GKD / OPD）训练器
#811 opened Jul 15, 2026 by winnnnnnd Loading…
1
Codex/code agent rl
#808 opened Jul 12, 2026 by RileyChen23 Loading…
Add MiniMind source course materials
#802 opened Jun 28, 2026 by syhyyds-git Loading…
Codex searchshortqa deepspeed
#791 opened Jun 2, 2026 by daiweidaichenzi Loading…
Fix readme windows details
#789 opened Jun 1, 2026 by Dujus Loading…
add train_agentic_rl_async.py 一个是 MiniMind 在多轮 Tool-Use 场景下的 异步 Agentic RL 训练脚本
#784 opened May 28, 2026 by littele-xuan Loading…
1
feat: 添加 macOS Metal (MPS) 设备支持
#780 opened May 25, 2026 by shiguol Loading…
2
适配昇腾NPU
#770 opened May 18, 2026 by yanghw116 Loading…
1
fix: guard against empty/filtered LLM responses in chat_api.py
#769 opened May 18, 2026 by qizwiz Loading…
[fix] 更新.gitignore文件，添加忽略目录；修改web_demo.py，优化样式和功能
#762 opened May 10, 2026 by 1Dreamer666 Loading…
1
chore(deps): 使用uv pyproject.toml替代requirements.txt管理依赖；增加vscode debug 配置，方便debug。
#756 opened May 5, 2026 by 100apps Loading…
[feat] add dapo algorithm
#708 opened Mar 27, 2026 by LittleExian Loading…
[add] add gating term on po algorithm
#664 opened Feb 3, 2026 by vanking20000918 Loading…
2
add muon optimizer
#663 opened Feb 2, 2026 by guo-sj Loading…
[mod & add] fix spo algorithm, add dapo and cispo algorithm in the RLAIF part.
#658 opened Jan 30, 2026 by vanking20000918 Loading…
4
perf: merge LoRA weights into model for inference
#599 opened Dec 23, 2025 by whiteswordLI Contributor Loading…
8
feat: add merge_lora.py to support merging LoRA weights into base model
#569 opened Dec 5, 2025 by dyhuachi Contributor Loading…
1
ProTip! Follow long discussions with comments:>50.