Trl Training
by huggingfaceabc20ae526d8Apache-2.0Listed Oct 8, 2026Updated Oct 8, 2026
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
Only the file list is public. File contents are available once the skill is installed in a workspace.
| Path | Size | Type |
|---|---|---|
| SKILL.md | 8.6 KB | text/markdown |
Source and attribution
Source:huggingface/skillsinskills/trl-trainingat commitabc20ae
License: Apache-2.0
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from huggingface/skills
Huggingface Zerogpu
huggingface
Guidance for writing and reviewing Gradio apps that run on Hugging Face Spaces ZeroGPU hardware.
Huggingface Trackio
huggingface
Guides logging, alerting on, and retrieving ML training metrics with the Trackio experiment tracking library.
Huggingface Papers
huggingface
Fetches Hugging Face paper pages as markdown and queries the papers API for metadata, links, search and daily papers.
Huggingface Local Models
huggingface
Guides selecting and running GGUF models locally with llama.cpp, covering Hub search, quant choice, and local serving.
Huggingface Gradio
huggingface
Reference guide for building Gradio web UIs and ML demos in Python, covering components, layouts, events and chatbots.
Huggingface Datasets
huggingface
Guides read-only Hugging Face Dataset Viewer API calls to explore, search, filter, and download dataset rows.
More in AI & Agents
Skill Development
anthropics
Guides creation of Claude Code plugin skills, covering structure, descriptions, progressive disclosure and validation.
Plugin Structure
anthropics
Guides the structure, manifest, and component layout of Claude Code plugins.
Command Development
anthropics
Guides creation of Claude Code slash commands, covering structure, YAML frontmatter, arguments and plugin features.
Claude Md Improver
anthropics
Audits CLAUDE.md files in a repository, scores their quality, and applies approved targeted improvements.
Google Cloud Solution Agentic Ai Data Science Workflow
Guides design of a multi-product agentic data science architecture on Google Cloud, from requirements to deployment and validation.
Google Cloud Solution Agentic Ai Borderless Data Lakehouse
Guides design of a borderless multicloud open data lakehouse on Google Cloud, from requirements discovery to deployment and validation.