CUDA · Model hubs and datasets

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

JimLiu/science-skills

Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.

huggingface/skills

A skill your agent uses when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose - eval - keep/revert loop…

RightNow-AI/AutoMegaKernel

Covers the rules for writing Gradio Spaces on ZeroGPU hardware: the @spaces.GPU decorator, duration and quota tuning, process isolation and CUDA build limits.

huggingface/skills

Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP, launching distributed training (paired…

NVIDIA/cosmos-framework

Guide to using Mamba selective state-space models for linear-time sequence modeling, from the Mamba block and pretrained checkpoints to Mamba-2 and speed comparisons.

Orchestra-Research/AI-Research-SKILLs

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU.

sickn33/agentic-awesome-skills

Continue KERMT pretraining on a custom SMILES corpus with a groverbase, cmim, or hybrid checkpoint.

NVIDIA/skills

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.

NVIDIA/skills

Finetune a pretrained KERMT encoder on a labeled CSV. An agent skill from NVIDIA/skills.

NVIDIA/skills

Use this operating skill for Tencent-Hunyuan/HunyuanVideo text-to-video setup, checkpoint layout, inference commands, Gradio launch, and CUDA/FP8/xDiT troubleshooting.

VectorSpaceLab/AREX-Skill

Install, manage, and run ComfyUI instances. An agent skill from sundial-org/awesome-openclaw-skills.

sundial-org/awesome-openclaw-skills