Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
-
Updated
Jun 12, 2025 - Python
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
SGLang is a fast serving framework for large language models and vision language models.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4v, Phi4, ...) (AAAI 2025).
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Comprehensive benchmark of 44 open source language models across creative writing, logic puzzles, counterfactual reasoning, and programming tasks. Tested on Apple M4 Max with detailed performance analysis.
Combining OCR for text extraction with LLMs for accurate, efficient document structuring.
MultiPage Invoice Parser
Repository for BabyLM competition on 3 models in Strict and Strict-small tracks
AlphaExtract is a sophisticated PDF summarization tool that combines cutting-edge AI technology with efficient document processing. The project is built using Python and leverages Meta's LLaMA 4 MOE Maverick model along with Groq's inference engine to provide fast and accurate PDF summaries.
Offline AI journaling app that gives insights based on your entries and runs locally with no cloud or data sharing.
# Open Source Language Model BenchmarkThis repository evaluates 43 open source language models across tasks like creative writing and programming. 🚀 It offers insights into model performance, showing that speed does not always equal accuracy. 🐱💻## OverviewThis benchmark evaluates where we currently stand with open source language models, exa
Streamlit ChatBot App powered by RAG
EcoSnap is a Python-based web application for waste classification and sustainability recommendations.
JBUD is a local AI journaling assistant that prioritizes your privacy and security. With features like smart journaling and AI insights, you can reflect on your thoughts without any data sharing. 📝💻
AlphaExtract is a sophisticated PDF summarization tool that combines cutting-edge AI technology with efficient document processing. The project is built using Python and leverages Meta's LLaMA 4 MOE Maverick model along with Groq's inference engine to provide fast and accurate PDF summaries.
Add a description, image, and links to the llama4 topic page so that developers can more easily learn about it.
To associate your repository with the llama4 topic, visit your repo's landing page and select "manage topics."