Instructions to use M37labsorg/ade-extract-3b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use M37labsorg/ade-extract-3b-v1 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("M37labsorg/ade-extract-3b-v1")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use M37labsorg/ade-extract-3b-v1 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 M37labsorg/ade-extract-3b-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf M37labsorg/ade-extract-3b-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf M37labsorg/ade-extract-3b-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf M37labsorg/ade-extract-3b-v1: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 M37labsorg/ade-extract-3b-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf M37labsorg/ade-extract-3b-v1: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 M37labsorg/ade-extract-3b-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf M37labsorg/ade-extract-3b-v1:Q4_K_M

Use Docker

docker model run hf.co/M37labsorg/ade-extract-3b-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use M37labsorg/ade-extract-3b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "M37labsorg/ade-extract-3b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "M37labsorg/ade-extract-3b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/M37labsorg/ade-extract-3b-v1:Q4_K_M

Ollama
How to use M37labsorg/ade-extract-3b-v1 with Ollama:
```
ollama run hf.co/M37labsorg/ade-extract-3b-v1:Q4_K_M
```
Unsloth Desktop

How to use M37labsorg/ade-extract-3b-v1 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "M37labsorg/ade-extract-3b-v1"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "M37labsorg/ade-extract-3b-v1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use M37labsorg/ade-extract-3b-v1 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "M37labsorg/ade-extract-3b-v1"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "M37labsorg/ade-extract-3b-v1"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "M37labsorg/ade-extract-3b-v1",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use M37labsorg/ade-extract-3b-v1 with Docker Model Runner:
```
docker model run hf.co/M37labsorg/ade-extract-3b-v1:Q4_K_M
```

Lemonade

How to use M37labsorg/ade-extract-3b-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull M37labsorg/ade-extract-3b-v1:Q4_K_M

Run and chat with the model

lemonade run user.ade-extract-3b-v1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use M37labsorg/ade-extract-3b-v1 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "M37labsorg/ade-extract-3b-v1"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default M37labsorg/ade-extract-3b-v1

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use M37labsorg/ade-extract-3b-v1 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "M37labsorg/ade-extract-3b-v1"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "M37labsorg/ade-extract-3b-v1" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

ade-extract-3b-v1

Published by M37 Labs (M37labsorg), the organisation of Hugging Face user engagepy, who maintains it. Built with SLM Forge.

Fine-tuned locally with SLM Forge on 2026-09-25.

Goal: Rebuild ADE Extract as a consistent JSON-only information extractor: report only facts explicitly stated in the text, use null for missing optional details, and return an empty events list when no adverse effect is stated. Train a clean adapter from the original base; treat the result as an experimental extraction aid, not medical advice, and do not claim commercial clearance for the ADE Corpus v2 data unless its license is verified. Base model: mlx-community/Qwen2.5-3B-Instruct-4bit Runs on: Apple Silicon Macs with 8 GB unified memory or more.

Lineage

SFT (job 50): train_loss 0.018, peak_mem_gb 7.15, val_loss_start 0.875, val_loss 0.025

Usage

pip install mlx-lm
mlx_lm.generate --model M37labsorg/ade-extract-3b-v1 --prompt "Hello"

Recommended sampling

{
  "temperature": 0.7,
  "top_p": 0.95
}

System prompt

Extract only what the text explicitly states. Return only valid JSON in exactly this shape: {"events":[{"drug":null,"adverse_effect":"...","evidence_span":"...","severity":null,"dosage":null,"action_taken":null}]}. Include one event per explicitly described adverse effect. Fill drug, adverse_effect, severity, dosage, and action_taken only when each is stated in the text; otherwise use JSON null. Do not infer a drug-event link from timing alone, or infer causality, severity, dosage, or actions. Quote the shortest exact, contiguous evidence span supporting the event. If no adverse effect is stated, return {"events":[]}. This is an extraction aid, not medical advice.

Run it anywhere (GGUF)

GGUF builds of this model, for llama.cpp, Ollama and LM Studio:

ade-extract-3b-v3-Q4_K_M.gguf (Q4_K_M, 1.80 GB)
ade-extract-3b-v3-Q8_0.gguf (Q8_0, 3.06 GB)

llama-cli -m ade-extract-3b-v3-Q4_K_M.gguf -p "Hello"   # llama.cpp
ollama run hf.co/M37labsorg/ade-extract-3b-v1:Q4_K_M   # Ollama

In LM Studio, search for the repository or load the .gguf file.

Licence & attribution

This model is a fine-tune of mlx-community/Qwen2.5-3B-Instruct-4bit and is subject to its licence: Qwen Research licence (https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE).

What it asks of you: Research and non-commercial use only; a commercial use needs a licence from Alibaba Cloud.

See LICENSE-BASE-MODEL.md, and the base model's own licence files where they could be included, in this folder.

Intended use & limitations

A small model fine-tuned for one narrow task on a few thousand examples. It makes mistakes, including confident ones. Check its outputs, and do not use it on its own for medical, legal, financial or safety-critical decisions.

Downloads last month: 74

Safetensors

Model size

3B params

Tensor type

U32

F16

MLX

Hardware compatibility

4-bit

Model tree for M37labsorg/ade-extract-3b-v1

Base model

Qwen/Qwen2.5-3B

Finetuned

mlx-community/Qwen2.5-3B-Instruct-4bit

Adapter

(7)

this model