jasonvanf/llama-trl
LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
This project helps machine learning engineers customize LLaMA language models to follow specific instructions or generate particular kinds of text. It takes a base LLaMA model and instruction-following datasets as input, and outputs a fine-tuned LLaMA model that is better at specific tasks. The ideal user is an ML engineer working with large language models.
238 stars. No commits in the last 6 months.
Use this if you need to adapt a LLaMA model to perform very specific instruction-following tasks without retraining from scratch, using techniques like PPO and LoRA.
Not ideal if you are looking for a pre-trained, ready-to-use model or a no-code solution for general text generation.
Stars
238
Forks
24
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jasonvanf/llama-trl"
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