unsloth
LLM fine-tuner
A Python-based framework for fine-tuning large language models to achieve improved performance with reduced memory usage.
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory
19k stars
129 watching
1k forks
Language: Python
last commit: almost 2 years agoLinked from 2 awesome lists
aifine-tuningfinetuninggemmagemma2llamallama3llmllmsloramistralphi3qloraunsloth
hannibal046/awesome-llm
amrzv/awesome-colab-notebooksRelated projects:
| Repository | Description | Stars |
|---|---|---|
 opengvlab/llama-adapter | An implementation of a method for fine-tuning language models to follow instructions with high efficiency and accuracy | 5,775 |
 alpha-vllm/llama2-accessory | An open-source toolkit for pretraining and fine-tuning large language models | 2,732 |
 hiyouga/llama-factory | A tool for efficiently fine-tuning large language models across multiple architectures and methods. | 36,219 |
 lightning-ai/lit-llama | An implementation of a large language model using the nanoGPT architecture | 6,013 |
 skypilot-org/skypilot | A framework for running AI and batch workloads on any infrastructure, offering unified execution, cost savings, and high GPU availability. | 6,905 |
 haotian-liu/llava | A system that uses large language and vision models to generate and process visual instructions | 20,683 |
 young-geng/easylm | A framework for training and serving large language models using JAX/Flax | 2,428 |
 lyogavin/airllm | Optimizes large language model inference on limited GPU resources | 5,446 |
 tloen/alpaca-lora | Tuning a large language model on consumer hardware using low-rank adaptation | 18,710 |
 freedomintelligence/llmzoo | A platform providing data, models, and evaluation benchmarks for large language models to promote accessibility and democratization of AI technology | 2,938 |
 ericlbuehler/mistral.rs | A high-performance LLM inference framework written in Rust | 4,677 |
 pytorch/torchtune | A PyTorch library for easily authoring and experimenting with large language models | 4,479 |
 modelscope/ms-swift | A framework for efficient fine-tuning and deployment of large language models | 4,659 |
 nlpxucan/wizardlm | Large pre-trained language models trained to follow complex instructions using an evolutionary instruction framework | 9,295 |
 ggerganov/llama.cpp | Enables LLM inference with minimal setup and high performance on various hardware platforms | 69,185 |