Fine Tuning skills

Microsoft Foundry

microsoft

End-to-end management for Microsoft Foundry agents.

Axolotl Skill

davila7

Expert guidance for fine-tuning LLMs with Axolotl.

Implementing LLMs with LitGPT

davila7

Train and implement LLMs efficiently using Lightning AI.

Transformers

k-dense-ai

Leverage Hugging Face models for diverse AI tasks.

Fine-Tuning with TRL

davila7

Align language models with human preferences using reinforcement learning.

N

Nemotron Retrieval Recipes

nvidia

Streamline your workflow with Nemotron embedding and reranking.

Quantized Export

wshobson

Efficiently export fine-tuned models for deployment.

P

PEFT Fine-Tuning

davila7

Efficiently fine-tune large language models with minimal resources.

Hugging Face LLM Trainer

huggingface

Train and fine-tune models on Hugging Face Jobs effortlessly.

Train Sentence Transformers

huggingface

Efficiently train and fine-tune sentence-transformers models.

Axolotl

nousresearch

Fine-tune LLMs with YAML configurations.

TRL Fine-Tuning

nousresearch

Align language models with human preferences using TRL.

E

Eval Harness First

wshobson

Essential setup for fine-tuning AI models.

L

LoRA & QLoRA Recipes

wshobson

Fine-tune your models with best-practice configurations.

Fine-Tuning Method Selection

wshobson

Streamline your fine-tuning decisions effectively.

P

PEFT Fine-Tuning

nousresearch

Efficiently fine-tune large LLMs with limited resources.

F

Fine-Tuning on Microsoft Foundry

microsoft

Efficiently fine-tune models with SFT, DPO, or RFT.

Nemotron ASR Customization

nvidia

Streamline ASR model fine-tuning for specific domains.

OpenVLA-OFT

orchestra-research

Fine-tune OpenVLA for robot action generation.

O

OpenPI Fine-Tuning and Serving

orchestra-research

Fine-tune and serve OpenPI models for robotics tasks.

Llama Factory

davila7

Expert guidance for fine-tuning LLMs with LLaMA-Factory.

L

LLM Operations

davila7

Streamline your LLM workflows with advanced techniques.

U

Unsloth

nousresearch

Accelerate LoRA/QLoRA fine-tuning with less VRAM.