FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
LLM post-training with TRL v1.0.0
Use this resource to fine-tune a language model with SFT, DPO or reinforcement learning
New
- 364 downloads
- 110 likes
- 244 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install llm-post-training-trlWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent picks the right method (SFT for instruction tuning, DPO for preference alignment, PPO or GRPO for reward optimization) and writes the training pipeline with TRL and Transformers. You get the training code and its settings.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: quick start and workflows (full RLHF pipeline)
- references/sft-training.md and references/dpo-variants.md: SFT settings and DPO variants
- references/reward-modeling.md and references/online-rl.md: reward models and online RL
Good fit for
- You want to align a model on chosen and rejected response pairs
- You want to adapt an open model to your own instructions
Not for
Tags
- trl
- sft
- dpo
- rlhf
- llm
About
You say
“Fine-tune this Qwen model on my instruction set, then switch to DPO with my preference pairs.”
Skill published by davila7 under the MIT license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to fine-tune a language model with SFT, DPO or reinforcement learning
- Review and adjust the result
Content preview
Files
- LICENSE1.1 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/dpo-variants.md4.4 KB
- references/online-rl.md2 KB
- references/reward-modeling.md2.7 KB
- references/sft-training.md3.3 KB
- SKILL.md11.7 KB
Origin and licence
Listed unmodified
- Author
- davila7
- Source
- github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/post-training-trl-fine-tuning
- Licence
- MIT
Notice
« post-training-trl-fine-tuning » (davila7, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…