Loading...
Loading...
Found 17 Skills
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
Reference — Complete Foundation Models framework guide covering LanguageModelSession, @Generable, @Guide, Tool protocol, streaming, dynamic schemas, built-in use cases, and all WWDC 2025 code examples
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
Use when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession, structured output, Tool protocol, iOS 26 AI integration.
Generate chat completions using Sarvam AI's Sarvam-M model. Use when the user needs AI chat, text generation, question answering, or reasoning in Indian languages. Sarvam-M is a 24B parameter model with hybrid thinking, superior Indic language understanding, and OpenAI-compatible API. Free to use.
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on 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 scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.
Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.
Expert skill for Open-AutoGLM, an AI phone agent framework that controls Android/HarmonyOS/iOS devices via natural language using the AutoGLM vision-language model
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.