awesome-totally-open-chatgpt
A list of totally open alternatives to ChatGPT
5k stars
93 watching
195 forks
last commit: over 1 year ago
Linked from 3 awesome lists
alternativeawesomeawesome-listawesome-listschatgptopen-source
Awesome Totally Open Chatgpt | |||
yaodongC/awesome-instruction-dataset | 1,071 | 9 months ago | : A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca) |
The list / togethercomputer/OpenChatKit | |||
spaces/togethercomputer/OpenChatKit | |||
The list / LAION-AI/Open-Assistant | |||
huggingface.co/OpenAssistant | |||
r/OpenAssistant/ | |||
The list / tatsu-lab/stanford_alpaca / Other LLaMA-derived projects: | |||
pointnetwork/point-alpaca | 406 | over 1 year ago | Released weights recreated from Stanford Alpaca, an experiment in fine-tuning LLaMA on a synthetic instruction dataset |
tloen/alpaca-lora | 18,564 | 2 months ago | Code for rproducing the Stanford Alpaca results using low-rank adaptation (LoRA) |
ggerganov/llama.cpp | 65,779 | 2 days ago | Ports for inferencing LLaMA in C/C++ running on CPUs, supports alpaca, gpt4all, etc |
setzer22/llama-rs | 6,062 | 3 months ago | Rust port of the llama.cpp project |
juncongmoo/chatllama | 1,203 | over 1 year ago | Open source implementation for LLaMA-based ChatGPT runnable in a single GPU |
Lightning-AI/lit-llama | 5,967 | 29 days ago | Implementation of the LLaMA language model based on nanoGPT |
nomic-ai/gpt4all | 69,594 | 9 days ago | Demo, data and code to train an assistant-style large language model with ~800k GPT-3.5-Turbo Generations based on LLaMA |
hpcaitech/ColossalAI#ColossalChat | 38,645 | 11 days ago | An open-source solution for cloning ChatGPT with a complete RLHF pipeline |
lm-sys/FastChat | 36,527 | 13 days ago | An open platform for training, serving, and evaluating large language model based chatbots |
nsarrazin/serge | 5,645 | 8 days ago | A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API |
The list / THUDM/ChatGLM-6B | |||
Akegarasu/ChatGLM-webui | 1,921 | about 1 year ago | Alternative Web UI: |
silver/chatglm-6b-slim | Slim version (remove 20K image tokens to reduce memory usage): | ||
lich99/ChatGLM-finetune-LoRA | 724 | about 1 year ago | Fintune ChatGLM-6b using low-rank adaptation (LoRA): |
tensorchord/modelz-ChatGLM | 15 | over 1 year ago | Deploying ChatGLM on Modelz: |
Basaran | 1,289 | 9 months ago | Docker image with built-on playground UI and streaming API compatible with OpenAI, using : |
The list / bigscience-workshop/xmtf | |||
bigscience/bloomz | |||
bigscience/mt0-base | |||
The list / databrickslabs/dolly | |||
dolly v2 12B commercial commercially available model | |||
dolly v1 6b model card | |||
The list / LianjiaTech/BELLE | |||
English readme | 7,833 | 7 months ago | |
The list / ethanyanjiali/minChatGPT | |||
huggingface.co/ethanyanjiali/minChatGPT | |||
The list / cerebras/Cerebras-GPT | |||
Announcement | |||
Models with other amount of parameters | |||
The list / h2oai/h2ogpt | |||
h2oGPT 20B | |||
🤗 h2oGPT 12B #1 | |||
🤗 h2oGPT 12B #2 | |||
The list / mlc-ai/web-llm | |||
https://mlc.ai/web-llm | |||
The list / Stability-AI/StableLM | |||
huggingface.co/spaces/stabilityai/stablelm-tuned-alpha-chat | |||
StableVicuna | 15,842 | 6 months ago | an RLHF fine-tune of Vicuna-13B v0, which itself is a fine-tune of LLaMA-13B |
The list / clue-ai/ChatYuan | |||
A bit translated readme to English | 4,507 | over 1 year ago | |
The list / OpenLMLab/MOSS | |||
English readme | 11,929 | 3 months ago |