What are the system requirements for Liu?
Python version ≥3.10 and ≤3.12, CUDA ≥12.4 and ≤12.8, and at least 2 GPUs are required.
L
Liu MCP Server
@modelscope
Basic information
About Liu MCP Server
No overview available yet
Liu MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Trinity-RFT": {
"command": "docker",
"args": [
"build",
"-f",
"scripts/docker/Dockerfile",
"-t",
"trinity-rft:latest",
"."
]
}
}
}Liu MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Liu?
Liu is a general‑purpose, flexible and easy‑to‑use framework for reinforcement fine‑tuning (RFT) of large language models. It supports diverse application scenarios and serves as a unified platform for exploring advanced RL paradigms, with capabilities for synchronous/asynchronous, on‑policy/off‑policy, and online/offline training.
How to use Liu?
Install Liu via pip install trinity-rft==0.2.1 or from source (Python ≥3.10, CUDA ≥12.4, at least 2 GPUs required). Prepare a model and dataset from Huggingface or ModelScope, then launch a web interface with trinity studio --port 8080 to configure and run the RFT process, or use trinity run --config <config_path> on the command line after starting a Ray cluster.
Key features of Liu
- Unified RFT core supporting multiple training modes.
- First‑class agent‑environment interaction handling.
- Optimized data pipelines with active management.
- Modular, decoupled architecture for easy adoption.
- Web‑based graphical interfaces for low‑code usage.
Use cases of Liu
- Adapting LLMs to new multi‑turn or multi‑step agentic scenarios.
- Developing custom RL algorithms with plug‑and‑play classes.
- Low‑code monitoring and tracking of the learning process.
- Fine‑tuning models on reasoning tasks (e.g., GSM8k with GRPO).
- Running offline learning via DPO or SFT.
Frequently asked questions
Which models and datasets are supported?
Liu supports most datasets and models from Huggingface and ModelScope, downloaded via `huggingface-cli` or `modelscope`.
How do I run a typical RFT process?
After installing and starting a Ray cluster, run `trinity run --config <config_path>` or use the web interface’s “Run” button after configuration.
Does Liu support multi‑turn and agentic interactions?
Yes, it supports first‑class agent‑environment interaction with lagged feedback, long‑tailed latencies, and graceful failure handling for multi‑turn tasks.
Can I use Liu for offline learning?
Yes, Liu supports offline learning modes, for example through DPO or SFT, as described in its tutorials.
More Other MCP servers
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
15.9K
Screenpipe
screenpipeYC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
22.0K
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
14.8K
Lemon.io
lemon-ioRequest dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
Handl
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments