欢迎访问我们的 ModelScope 中文社区，体验热门模型的国内高速下载和一键部署！
https://modelscope.cn/organization/OpenBuddy
Our curated list of models, which possess impressive capabilities within their respective sizes.
This models are intended for use in vllm or transformers.
https://huggingface.co/collections/OpenBuddy/our-selected-models-65369270912eef259074d3dc
Quantized models are also available in this collection: https://huggingface.co/collections/OpenBuddy/quantized-models-65d1e085bf849f3b7982a1a2
GGUF is a format defined by llama.cpp. It is optimized for personal-level CPU/GPU inference.
GGUF models are available on Ollama, a platform for deploying and serving models for personal-level CPU/GPU inference.
After you have installed Ollama , you can deploy our model with a single command:
ollama run openbuddy/openbuddy-llama3-8b-v21.1-8k
You can also find more of our models here: https://ollama.com/openbuddy
This models are intended for use in vllm or transformers.
https://huggingface.co/collections/OpenBuddy/quantized-models-65d1e085bf849f3b7982a1a2
More models are available on our HuggingFace: https://huggingface.co/OpenBuddy