Browse Skills

Provides expert assistance for configuring and running LLM fine-tuning with Axolotl, covering YAML configs, 100+ model architectures, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, and multimodal support.

SentencePiece is a language-independent tokenizer that works on raw Unicode text without pre-tokenization. It supports BPE and Unigram algorithms for fast, deterministic vocabulary training, ideal for multilingual NLP models and CJK languages.

Rust-based tokenization library for NLP that processes 1GB of text in under 20 seconds. Supports BPE, WordPiece, and Unigram algorithms, custom vocabulary training, and seamless transformers integration for research and production.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

A skill for using RWKV, the RNN-Transformer hybrid model that offers linear-time inference, infinite context, and constant memory. Covers installation, text generation, long context processing, fine-tuning, and comparison with Transformers.

A minimalist, educational GPT implementation in ~300 lines of code. Ideal for learning transformer architectures from scratch; supports training on Shakespeare (CPU) or reproducing GPT-2 on OpenWebText (multi-GPU).

Implements Mamba state-space models achieving O(n) complexity for sequence modeling. Enables 5× faster inference, million-token sequences, and no KV cache. Ideal for streaming and long-context applications.

Implements and trains LLMs using LitGPT with 20+ architectures like Llama, Gemma, Phi. Use for clean model implementations, understanding architectures, or production fine-tuning with LoRA/QLoRA. Single-file, no abstraction layers.

Orchestrates end-to-end autonomous AI research using a two-loop architecture for rapid experimentation and synthesis. Use for starting research projects, running autonomous experiments, or managing multi-hypothesis efforts.

Quantize large language models to 4/3/2-bit precision without calibration data, enabling faster quantization and deployment with vLLM or HuggingFace Transformers.

Equips AI agents with full web browsing capabilities via a CDP proxy, including dynamic page interaction, media extraction, and site pattern learning.

Automates the Fluid Framework client release process: minor and patch releases, branching, version bumps, changelogs, and type test updates. Supports interactive and autonomous modes with auto-detection of release state.