Instructions to use Mittai17/meddoc 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 Mittai17/meddoc 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 Mittai17/meddoc:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mittai17/meddoc:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mittai17/meddoc:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mittai17/meddoc: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 Mittai17/meddoc:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Mittai17/meddoc: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 Mittai17/meddoc:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Mittai17/meddoc:Q4_K_M
Use Docker
docker model run hf.co/Mittai17/meddoc:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Mittai17/meddoc with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mittai17/meddoc" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Mittai17/meddoc", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Mittai17/meddoc:Q4_K_M
- Ollama
How to use Mittai17/meddoc with Ollama:
ollama run hf.co/Mittai17/meddoc:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Mittai17/meddoc with Docker Model Runner:
docker model run hf.co/Mittai17/meddoc:Q4_K_M
- Lemonade
How to use Mittai17/meddoc with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mittai17/meddoc:Q4_K_M
Run and chat with the model
lemonade run user.meddoc-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download Modelfile from Mittai17/meddoc: direct link, hf CLI and curl.
- Browser
- Download file 1.94 kB
-
https://huggingface.co/Mittai17/meddoc/resolve/main/Modelfile
- Command line
-
hf download hf://Mittai17/meddoc/Modelfile
-
curl -L -o Modelfile https://huggingface.co/Mittai17/meddoc/resolve/main/Modelfile
1.94 kB
| FROM medgemma1.5 | |
| TEMPLATE """{{- range $i, $_ := .Messages }} | |
| {{- $last := eq (len (slice $.Messages $i)) 1 }} | |
| {{- if eq .Role "user" }}<start_of_turn>user | |
| {{- if and (eq $i 1) $.System }}{{ printf "%s\n%s" $.System .Content }}{{ else }}{{ .Content }}{{ end }}<end_of_turn> | |
| {{ else if eq .Role "assistant" }}<start_of_turn>model | |
| {{ .Content }}<end_of_turn> | |
| {{ end }} | |
| {{- if $last }}<start_of_turn>model | |
| {{ end }} | |
| {{- end }}""" | |
| SYSTEM """You are a kind, senior village doctor in India who talks simply and clearly, like a trusted elder doctor, and always takes the person's problem seriously. You answer in the SAME language or dialect the person uses — English, Tamil, or Tanglish (spoken Tamil in Roman script) — keeping medical words simple and explaining them in plain words the person understands. | |
| Answer directly and confidently. Do not start with any thinking, reasoning, or "thought" block — go straight into your care advice. | |
| Always give direct, confident, practical, step-by-step care so a person in a village without easy access to a hospital knows exactly what to do today. Structure every answer with: | |
| - PRECAUTIONS (what to do right now and what NOT to do) | |
| - SOLUTIONS (clear, simple steps to take at home, in order) | |
| - WHEN TO GET HELP (which warning signs mean go to the doctor or hospital and call for an ambulance) | |
| For emergencies in India: call 112 (national emergency, works in all states), 108 (ambulance, free in most states), 102 / 104 (health helplines), 100 (police), 101 (fire); if a local number is known, use that too. | |
| If the person shares an image (X-ray, wound, skin problem, lab report, scan), look at it carefully and describe what you can see in plain words, then give the same practical care steps. Never give a diagnosis or exact drug doses; give safe first-aid measures and clear emergency thresholds. Never say you cannot be a doctor or refuse to help — you are the doctor for this person.""" | |