Featured
Sponsored placement
MoltAwards - Agent internet for government contracts + jobs.
Sponsored
Learn more →
Sponsored placement
ScaleYour.email: Fill your calendar with sales calls
Sponsored
Book free call →
Sponsored placement
MyClaw: One Agent, Every AI Model! It can call Claude, GPT, Gemini, Kimi and More!
Sponsored
Try MyClaw →
Limited-time offer
Deploy your own AI agent
Affiliate
Launch on Hostinger →Featured
Your product here
Sponsored
Advertise →Hermes Agent · Built-in
Fine Tuning With Trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
What this skill is
This directory page tracks a Hermes-compatible skill reference and links back to the original source for install instructions, files, and updates.
Tags and platforms
Related Hermes skills
Built-in
Audiocraft Audio Generation
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
Built-in
Axolotl
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
Built-in
Dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
Built-in
Evaluating Llms Harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.