bayjarvis/llm
Fine-tuning, DPO, RLHF, RLAIF on LLMs - Qwen3, Zephyr 7B GPTQ with 4-Bit Quantization, Mistral-7B-GPTQ
This collection of projects helps AI practitioners and researchers adapt large language models (LLMs) like Qwen3 or Mistral-7B for specific tasks and better align their responses. You can take existing LLMs and your own specialized data or preference rankings to produce a customized, more accurate language model. It's designed for machine learning engineers, data scientists, and AI developers working on deploying or researching advanced LLM applications.
No commits in the last 6 months.
Use this if you need to customize the behavior of an open-source large language model for a particular application, improve its conversational alignment, or explore advanced training techniques like Mixture of Experts.
Not ideal if you are looking for a pre-trained, ready-to-use LLM without any customization, or if you don't have the technical expertise to train and fine-tune machine learning models.
Stars
15
Forks
—
Language
Python
License
—
Category
Last pushed
Jul 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/bayjarvis/llm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huawei-csl/SINQ
Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method...
SILX-LABS/QUASAR-SUBNET
QUASAR is a long-context foundation model and decentralized evaluation subnet built on Bittensor,
stackblogger/bitnet.js
BitNet.Js - A node.js implementation of the microsoft bitnet.cpp inference framework.
m96-chan/0xBitNet
Run BitNet b1.58 ternary LLMs with WebGPU — in browsers and native apps
AnswerDotAI/cold-compress
Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking...