Best fine-tuning skills, page 5

Fine-tune large LLMs with LoRA on limited GPU memory. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

[omh] Fine-tuning a model on your own data -- SFT, DPO, RLVR or a LoRA adapter: decide first whether prompting or retrieval already closes the gap, choose the method from the data you have, and…

rlaope/oh-my-hermes

Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nnscore), and search per-sample (guidance, cropratio) parameters.

NVIDIA/skills

Check progress for a detached KERMT run (pretrain, finetune, or any kermtrundetached invocation).

NVIDIA/skills

A skill your agent uses when validating an existing prognostic risk signature on an external bulk expression cohort with survival outcomes, producing risk scores, Kaplan-Meier curves, risk…

aipoch/medical-research-skills

A skill your agent uses when running prognostic survival analysis on a clinical cohort with time-to-event data to estimate univariate and multivariable Cox proportional hazards models, export result…

aipoch/medical-research-skills

AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and…

modu-ai/moai-adk

Preserve + publish a finished RL (SkyRL/GRPO) training checkpoint after the job terminates (completed at maxsteps OR early-stopped/scancelled) on an HPC cluster (Jupiter/Leonardo/Perlmutter).

open-thoughts/OpenThoughts-Agent

Launch, relaunch, or sweep STANDARD (non-agentic) SkyRL RL on CINECA Leonardo — GRPO on math/reasoning datasets (gsm8k, MATH/aime) and on-policy distillation (OPD, teacher→student) — via raw sbatch…

open-thoughts/OpenThoughts-Agent

Launch SFT via python -m hpc.launch --jobtype sft on any cluster (JSC Jupiter GH200, CINECA Leonardo A100, TACC Vista GH200), with EITHER backend — LLaMA-Factory (default) or axolotl (--sftbackend…

open-thoughts/OpenThoughts-Agent

Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal.

NVIDIA/skills

Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLflow tracking and checkpoint evidence.

NVIDIA/skills

A skill your agent uses when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or PAIDF Data Mining…

NVIDIA/skills

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.

NVIDIA/skills

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning.

NVIDIA/skills

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches.

NVIDIA/skills

NV-Tesseract AD Diffusion — diffusion-based anomaly detection and fine-tuning for multivariate time series.

NVIDIA/skills

NV-Tesseract Forecasting — transformer-based multivariate time series forecasting with DARR (context-enhanced kNN retrieval), interpretability, and fine-tuning.

NVIDIA/skills

InternVideo2-CLIP L14 (TAO videoclip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment.

NVIDIA/skills

DINOv3 continual self-supervised pre-training. An agent skill from NVIDIA/skills.

NVIDIA/skills

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning.

NVIDIA/skills

Apply ML/AI project delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems.

managedcode/Storage

Add any Hugging Face image or video model, checkpoint or LoRA to Guaardvark from a URL, list what is installed, and download registry models on request.

guaardvark/guaardvark

Builds generative AI applications on Amazon Bedrock. An agent skill from aws/agent-toolkit-for-aws.

aws/agent-toolkit-for-aws

Reference for the GRPO (Group Relative Policy Optimization) algorithm.

benchflow-ai/skillsbench

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO).

benchflow-ai/skillsbench

Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning

AgentToolkit/altk-evolve

Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation

ruvnet/ruflo

Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and…

nodetool-ai/nodetool

Train, evaluate, and export neural networks to Simulink in MATLAB.

matlab/matlab-agentic-toolkit

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization.

yonatangross/orchestkit

Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation.

NVIDIA/skills

Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist.

NVIDIA/skills

Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists.

NVIDIA/skills

Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count, failurecount, pixel-intensity histogram) across…

NVIDIA/skills

Generate AI videos for mature creative projects using Wan 2.2 Spicy (LoRA-tuned for NSFW, top recommended), Wan 2.6, Seedance 1.5, Vidu Q3-Pro, and other models with relaxed content policies via…

LeoYeAI/openclaw-master-skills

Expert prompt engineering for FLUX.2 [klein] image generation and editing model.

AnastasiyaW/codex-claude-code-config

Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks.

AnastasiyaW/codex-claude-code-config

Selects, deploys, and customizes AI models on Amazon SageMaker.

aws/agent-toolkit-for-aws

On-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt.

artokun/comfyui-mcp

Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend.

jinzhezenggroup/computational-chemistry-agent-skills

Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans…

NVIDIA/skills

Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти.

AnastasiyaW/codex-claude-code-config

Guided workflow for taking any ML codebase — including one with no experiment tracking at all, or one full of MLflow 2-era idioms — to a production-grade open-source MLflow 3 setup with…

pproenca/dot-skills

Analyze and apply AssemblyAI secret, region, consent, retention, deletion, and model-training controls.

jeremylongshore/tons-of-skills-marketplace

Gate Together AI client, batch, fine-tuning, and deployment changes with offline contract tests plus a protected bounded live lane.

jeremylongshore/tons-of-skills-marketplace

Analyze and diagnose Together AI authentication, billing, request, model, throttling, overload, batch, fine-tuning, and endpoint failures from redacted evidence.

jeremylongshore/tons-of-skills-marketplace

Prepare, submit, monitor, and disposition a Together AI fine-tuning job using SDK v2, validated training data, explicit cost approval, and separate deployment verification.

jeremylongshore/tons-of-skills-marketplace