dred0n

Pinned Repositories

OpenHands
🙌 OpenHands: Code Less, Make More
Language:Python36.3k 313 1.6k4.1k
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
Language:Python00
llmtune
4-Bit Finetuning of Large Language Models on One Consumer GPU
Language:Python00
LocalAI
:robot: Self-hosted, community-driven, local OpenAI-compatible API. Drop-in replacement for OpenAI running LLMs on consumer-grade GPU. LocalAI is a RESTful API to run GPTQ compatible models
Language:Go00
OpenDevin
🐚 OpenDevin: Code Less, Make More
Language:Python00
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
Language:Jupyter Notebook00
text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Language:Python00
evalplus
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Language:Python1.2k 8 186109
argh-steroids
Asteroids-like game using pygame
Language:Python15 4 36
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Language:Python30.1k 247 5.2k4.5k

dred0n's Repositories

dred0n/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
Language:Python00
dred0n/llmtune
4-Bit Finetuning of Large Language Models on One Consumer GPU
Language:Python00
dred0n/LocalAI
:robot: Self-hosted, community-driven, local OpenAI-compatible API. Drop-in replacement for OpenAI running LLMs on consumer-grade GPU. LocalAI is a RESTful API to run GPTQ compatible models
Language:Go00
dred0n/OpenDevin
🐚 OpenDevin: Code Less, Make More
Language:Python00
dred0n/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
Language:Jupyter Notebook00
dred0n/text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Language:Python00