How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf QuantFactory/medllama3-v20-GGUF:# Run inference directly in the terminal:
llama cli -hf QuantFactory/medllama3-v20-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 QuantFactory/medllama3-v20-GGUF:# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/medllama3-v20-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 QuantFactory/medllama3-v20-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/medllama3-v20-GGUF:Use Docker
docker model run hf.co/QuantFactory/medllama3-v20-GGUF:Quick Links
QuantFactory/medllama3-v20-GGUF
This is quantized version of ProbeMedicalYonseiMAILab/medllama3-v20 created using llama.cpp
Original Model Card
The model is a fine-tuned large language model on using publically available medical data.
Model Description
- Developed by: Probe Medical, MAILAB from Yonsei University
- Model type: LLM
- Language(s) (NLP): English
Training Hyperparameters
- Lora Targets: "o_proj", "down_proj", "v_proj", "gate_proj", "up_proj", "k_proj", "q_proj"
- Downloads last month
- 147
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf QuantFactory/medllama3-v20-GGUF:# Run inference directly in the terminal: llama cli -hf QuantFactory/medllama3-v20-GGUF: