misonsky/HiFT
memory-efficient fine-tuning; support 24G GPU memory fine-tuning 7B
This helps data scientists and ML engineers efficiently fine-tune large language models (LLMs) like Llama2-7B, even on GPUs with limited memory (24GB). You provide your pre-trained LLM and a dataset for a specific task (e.g., text classification, question answering), and it outputs a fine-tuned model ready for deployment. It's designed for practitioners working with LLMs who face memory constraints during the fine-tuning process.
No commits in the last 6 months. Available on PyPI.
Use this if you need to fine-tune a 7-billion parameter language model for tasks like text generation, classification, or question answering, but are constrained by a 24GB GPU memory limit.
Not ideal if you have ample GPU memory (e.g., 48GB or more) or if you are not working with large language models.
Stars
21
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
May 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/misonsky/HiFT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training