Hermes Skills
Every skill in the official Hermes Agent catalog, written up from the documentation, alongside the skills published as open-source repositories.
Explore guidesSkills that ship with Hermes Agent or install into it, each written up from the official documentation with its commands reproduced unchanged.
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
HuggingFace hf CLI: search/download/upload models, datasets.
llama.cpp local GGUF inference + HF Hub model discovery.
vLLM: high-throughput LLM serving, OpenAI API, quantization.
W&B: log ML experiments, sweeps, model registry, dashboards.
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
Embedding database for RAG and semantic search.
Zero-shot image classification and image-text search.
Pretrain LLMs at scale with PyTorch 4D parallelism.
DSPy: declarative LM programs, auto-optimize prompts, RAG.
Fast vector similarity search at billion scale.
TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.
Constrain LLM output with grammars; guarantee valid JSON.
Run PyTorch training across GPUs with minimal changes.
Fast BPE/WordPiece tokenization and custom vocab training.
Structured LLM outputs validated with Pydantic.
On-demand GPU cloud instances for ML training.
Vision-language chat: VQA, captioning, image dialogue.
Serverless GPU cloud for ML jobs and model APIs.
Curate LLM training data: dedupe, filter, PII redaction.
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Speed up long-sequence transformer training and inference.
Outlines: structured JSON/regex/Pydantic LLM generation.
Fine-tune large LLMs with LoRA on limited GPU memory.