Instructions to use OpenMed/maple-preview-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMed/maple-preview-4bit-mlx 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("OpenMed/maple-preview-4bit-mlx")

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
LM Studio

How to use OpenMed/maple-preview-4bit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OpenMed/maple-preview-4bit-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "OpenMed/maple-preview-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use OpenMed/maple-preview-4bit-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OpenMed/maple-preview-4bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OpenMed/maple-preview-4bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OpenMed/maple-preview-4bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use OpenMed/maple-preview-4bit-mlx 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 "OpenMed/maple-preview-4bit-mlx"

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 OpenMed/maple-preview-4bit-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OpenMed/maple-preview-4bit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OpenMed/maple-preview-4bit-mlx"

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 "OpenMed/maple-preview-4bit-mlx" \
  --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"

MaziyarPanahi commited on 12 days ago

Commit

e119204

verified ·

1 Parent(s): aeba65d

Add OpenMed validation model card

Browse files

Files changed (1) hide show

README.md +39 -0

README.md ADDED Viewed

	@@ -0,0 +1,39 @@

+---
+base_model: deepgrove/maple-preview
+base_model_relation: quantized
+language:
+  - en
+library_name: mlx
+license: mit
+pipeline_tag: text-generation
+tags:
+  - mlx
+  - maple
+  - mixture-of-experts
+  - quantized
+  - experimental
+  - openmed
+---
+# Maple Preview 4-bit MLX — experimental archive
+> **Do not deploy this export.** It is retained privately as a reproducibility
+> artifact for a failed development validation result.
+This OpenMed export was converted from
+[`deepgrove/maple-preview`](https://huggingface.co/deepgrove/maple-preview)
+revision `ac1ddd79d2b5cb4406f5d2bebdf95406ce505a07` with 4-bit affine
+quantization and group size 128. The included `openmed-maple-export.json`
+records the pinned source and runtime-code revisions and conversion settings.
+The checkpoint converted and loaded on Apple Silicon, but its synthetic
+structured-task run exhausted the 4,096-token generation budget before
+producing final JSON. Successful tensor conversion is not evidence of useful
+or safe generation. No clinical-quality, direct-identifier recall,
+critical-leakage, source-parity, or physical-device claim is made.
+See the validation table and reproducible export instructions in
+[`docs/maple-on-device.md`](https://github.com/maziyarpanahi/openmed/blob/master/docs/maple-on-device.md).
+Maple Preview is a research model, not a medical device. The upstream model is
+licensed under MIT; see the upstream repository for its license and model card.