huggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scrip...
Install this skill
or
95/100
Security score
The huggingface-llm-trainer skill was audited on Oct 1, 2026 and we found 1 security issue across 1 threat category. Review the findings below before installing.
Categories Tested
Security Issues
medium line 240
Upload instruction
SourceSKILL.md
| 238 | ``` |
| 239 | |
| 240 | **To use local scripts:** Upload to HF Hub first: |
| 241 | ```bash |
| 242 | hf repos create my-training-scripts --type model |
Scanned on Oct 1, 2026
View Security Dashboard