ai-agent

Fine-tune Nemotron-3 with workbench-example-nemotron-finetune

Fine-tune Nemotron-3 models with this example project, useful for founders working with AI agents, 74 GitHub stars
75 stars39 forksJupyter NotebookGuide quality 9/10Updated 4/15/2024100% free · open source
What it does

Fine-tunes a pre-trained Nemotron-3 8B model for specific use cases using NVIDIA's AI Workbench example project

When to use it
  • You need to adapt a large language model for a custom dataset or task
  • You're working with AI agents and want to improve their performance on a specific domain
  • You have a Jupyter Notebook environment and want to leverage NVIDIA's AI Workbench for fine-tuning
Ready-to-paste prompt
Run `!python fine_tune_nemotron.py --model nemotron-3-8b --dataset your_custom_dataset` to fine-tune the model on your custom dataset
Heads up: Ensure you have the required NVIDIA GPU drivers and CUDA version installed, as specified in the NVIDIA AI Workbench documentation, to avoid compatibility issues
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/workbench-example-nemotron-finetune && curl -fsSL https://workflowstacks.com/api/skills/workbench-example-nemotron-finetune/claude-skill -o ~/.claude/skills/workbench-example-nemotron-finetune/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions
Details
Creator
NVIDIA
Language
Jupyter Notebook
Category
ai-agent
Published
12/20/2023

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.