OpenChat-Cuda
Docker 应用程序 from el_pino's Repository
概述
A self-hosted, offline, ChatGPT-like chatbot with open source LLM support. 100% private, with no data leaving your device.
Please note that this version requires an NVIDIA GPU with the Unraid NVIDIA-DRIVER plugin.
运行时参数
- 网络用户界面
http://[IP]:[PORT:3000]/- 网络
bridge- 外壳
sh- 特权
- false
- 额外参数
--gpus all
模板配置
Local Model PathVariable
The local model path
- 目标
- MODEL
- 默认值
- /models/llama-2-7b-chat.bin
Model Download URLVariable
GGML Model Binary.
- 目标
- MODEL_DOWNLOAD_URL
- 默认值
- https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q4_0.bin
Model DirectoryPathrw
The local model directory to use as a cache
- 目标
- /models
- 默认值
- /mnt/user/appdata/models
Web UIPorttcp
Chat UI Port
- 目标
- 3000
- 默认值
- 3000
API PortPorttcp
HTTP API Port
- 目标
- 8000
- 默认值
- 8000
Number Of GPU LayersVariable
Layers to offload to GPU. Update this number if server fails to load.
- 目标
- N_GPU_LAYERS
- 价值
- 12
详细信息
存储库
ghcr.io/edgar971/open-chat-cuda:v1.0.6最后更新2026-05-31
初见2023-09-06
在Unraid 上运行 OpenChat-Cuda 。
OpenChat-Cuda 已被列入Unraid OS 的社区应用程序。探索Unraid ，构建灵活的家庭服务器、NAS 或家庭实验室。