fursovia

chatbot-ui

AI chat for every model.

path-to-senior-engineer-handbook

All the resources you need to get to Senior Engineer and beyond

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

SadTalker

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

PhotoMaker

PhotoMaker

vanna

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

axolotl

Go ahead and axolotl questions

mlx-examples

Examples in the MLX framework

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

ChatUI

The UI design language and React library for Conversational UI

mergekit

Tools for merging pretrained large language models.

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

flutter_chat_ui

Actively maintained, community-driven chat UI implementation with an optional Firebase BaaS.

sd-wav2lip-uhq

Wav2Lip UHQ extension for Automatic1111

Qwen-TensorRT-LLM

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

llm-autoeval

Automatically evaluate your LLMs in Google Colab

errant

ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.

prompt-lookup-decoding

bagel

A bagel, with everything.

lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

LLaMa2lang

Convenience scripts to finetune (chat-)LLaMa3 and other models for any language

C4_200M-synthetic-dataset-for-grammatical-error-correction

This dataset contains synthetic training data for grammatical error correction. The corpus is generated by corrupting clean sentences from C4 using a tagged corruption model. The approach and the dataset are described in more detail by Stahlberg and Kumar (2021) (https://www.aclweb.org/anthology/2021.bea-1.4/)

EditEval

An instruction-based benchmark for text improvements.

faster-SadTalker-API

The API server version of the SadTalker project. Runs in Docker, 10 times faster than the original!

openai_trtllm

OpenAI compatible API for TensorRT LLM triton backend

coedit

Official implementation of the paper "CoEdIT: Text Editing by Task-Specific Instruction Tuning" (EMNLP 2023)

sft-demos

Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.