ms-swift and LLM-Finetuning

A comprehensive production framework for fine-tuning hundreds of models across multiple training paradigms, while B is a lightweight educational repository demonstrating PEFT fine-tuning techniques—making them complementary resources where B's examples could inform workflows within A's ecosystem.

ms-swift
78
Verified
LLM-Finetuning
45
Emerging
Maintenance 22/25
Adoption 11/25
Maturity 25/25
Community 20/25
Maintenance 2/25
Adoption 10/25
Maturity 8/25
Community 25/25
Stars: 13,105
Forks: 1,255
Downloads:
Commits (30d): 89
Language: Python
License: Apache-2.0
Stars: 2,827
Forks: 725
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
No risk flags
No License Stale 6m No Package No Dependents

About ms-swift

modelscope/ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).

This framework helps AI developers and researchers customize large language models (LLMs) and multimodal large models (MLLMs) for specific tasks or datasets. It takes a base model and your specialized data, then outputs a fine-tuned model ready for deployment. This is for professionals building custom AI applications.

AI development machine learning engineering natural language processing computer vision model customization

About LLM-Finetuning

ashishpatel26/LLM-Finetuning

LLM Finetuning with peft

This project helps machine learning engineers and researchers adapt large language models (LLMs) like Llama 2, Falcon, or GPT-Neo-X to perform specific tasks using their own custom datasets. You provide an existing LLM and your unique text data, and it outputs a specialized version of that model ready for tasks such as answering domain-specific questions, generating tailored text, or improving chatbot performance. This is for professionals who need to customize powerful AI models without starting from scratch.

large-language-models natural-language-processing AI-model-customization machine-learning-engineering

Scores updated daily from GitHub, PyPI, and npm data. How scores work