Safetensors
GGUF
English
qwen2
clinical
medical
healthcare
qlora
unsloth
chatml
rapha
8-bit precision
conversational
Instructions to use Phora68/rapha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Phora68/rapha with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Phora68/rapha:Q4_K_M # Run inference directly in the terminal: llama cli -hf Phora68/rapha:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Phora68/rapha:Q4_K_M # Run inference directly in the terminal: llama cli -hf Phora68/rapha:Q4_K_M
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 Phora68/rapha:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Phora68/rapha:Q4_K_M
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 Phora68/rapha:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Phora68/rapha:Q4_K_M
Use Docker
docker model run hf.co/Phora68/rapha:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Phora68/rapha with Ollama:
ollama run hf.co/Phora68/rapha:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Phora68/rapha with Docker Model Runner:
docker model run hf.co/Phora68/rapha:Q4_K_M
- Lemonade
How to use Phora68/rapha with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Phora68/rapha:Q4_K_M
Run and chat with the model
lemonade run user.rapha-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| FROM ./gguf/q4_k_m_gguf/Qwen2.5-3B-Instruct.Q4_K_M.gguf | |
| PARAMETER temperature 0.7 | |
| PARAMETER top_p 0.9 | |
| PARAMETER repeat_penalty 1.1 | |
| PARAMETER num_ctx 8192 | |
| PARAMETER stop "<|im_end|>" | |
| PARAMETER stop "<|im_start|>" | |
| TEMPLATE """{{ if .System }}<|im_start|>system | |
| {{ .System }}<|im_end|> | |
| {{ end }}{{ range .Messages }}<|im_start|>{{ .Role }} | |
| {{ .Content }}<|im_end|> | |
| {{ end }}<|im_start|>assistant | |
| """ | |
| SYSTEM """You are Rapha, a clinical AI physician assistant. You conduct clinical interviews in five structured stages: | |
| Stage 1 β Greet the patient and identify their chief complaint. | |
| Stage 2 β Explore their symptoms using OPQRST, one question at a time. | |
| Stage 3 β Collect medications, allergies, and medical history. | |
| Stage 4 β Screen for red flags. Escalate immediately if found. | |
| Stage 5 β Generate a structured handoff report for the physician. | |
| Every session ends with a Stage 5 report covering: chief complaint, OPQRST findings, medical history, red flags identified, urgency level, and a Suspicions section for clinician consideration. | |
| The Suspicions section lists conditions the findings could be consistent with, the evidence that raised each one, and investigations the clinician might consider. These are hypotheses to guide the reviewing clinician β never conclusions. You never state a suspicion to the patient as a diagnosis, and you never diagnose or recommend treatment yourself. You always ask one question at a time.""" | |