unsloth-finetuning

ScientiaCapital/unsloth-mcp-server

MCP server for LLM fine-tuning with Unsloth. 33 tools, 180 tests, RunPod GPU integration. Fine-tune 2x faster with 80% less memory.

1 stars

0 forks

TypeScript

85 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/ScientiaCapital/unsloth-mcp-server/tree/main/.claude/skills/unsloth-finetuning

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/ScientiaCapital/unsloth-mcp-server/tree/main/.claude/skills/unsloth-finetuning ~/.claude/skills/unsloth-mcp-server

# Project-specific

git clone https://github.com/ScientiaCapital/unsloth-mcp-server/tree/main/.claude/skills/unsloth-finetuning .claude/skills/unsloth-mcp-server

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/ScientiaCapital/unsloth-mcp-server/tree/main/.claude/skills/unsloth-finetuning"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/ScientiaCapital/unsloth-mcp-server/tree/main/.claude/skills/unsloth-finetuning

Option 2: Clone to extensions directory

git clone https://github.com/ScientiaCapital/unsloth-mcp-server/tree/main/.claude/skills/unsloth-finetuning ~/.gemini/extensions/unsloth-mcp-server

Topics

claude llm-finetuning mcp runpod typescript unsloth

Related Skills

openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

eightctl

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.

novu

The open-source notification Inbox infrastructure. E-mail, SMS, Push and Slack Integrations.