How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Himitsui/MedMitsu-GGUF:# Run inference directly in the terminal:
llama-cli -hf Himitsui/MedMitsu-GGUF:Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Himitsui/MedMitsu-GGUF:# Run inference directly in the terminal:
./llama-cli -hf Himitsui/MedMitsu-GGUF:Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Himitsui/MedMitsu-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf Himitsui/MedMitsu-GGUF:Use Docker
docker model run hf.co/Himitsui/MedMitsu-GGUF:Quick Links
Included in this repo is the GGUF Quants for the finetune over the base, and/or instruct model.
(☯‿├┬┴┬┴┬┴┬┴┤(･_├┬┴┬┴┬┴┬┴┤･ω･)ﾉ
Hiya! This is my 11B Solar Finetune.
Included in the dataset I used to train are 32K Entries of Medical Data, 11K Rows of Raw Medical Text and lastly, 3K entries of Instruction Tasks (・_・ヾ)
Alpaca or Regular Chat Format Works Fine :)
(｡･ˇ_ˇ･｡) You should not use an AI model to verify and confirm any medical conditions due to the possibility of Hallucinations, but it is a good starting point (ﾉ◕ヮ◕)ﾉ*:･ﾟ✧
- Downloads last month
- 42
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf Himitsui/MedMitsu-GGUF:# Run inference directly in the terminal: llama-cli -hf Himitsui/MedMitsu-GGUF: