Instructions to use pipenetwork/GLM-5.2-REAP50-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/GLM-5.2-REAP50-MLX-4bit 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("pipenetwork/GLM-5.2-REAP50-MLX-4bit")

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 pipenetwork/GLM-5.2-REAP50-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/GLM-5.2-REAP50-MLX-4bit"

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": "pipenetwork/GLM-5.2-REAP50-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/GLM-5.2-REAP50-MLX-4bit 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 "pipenetwork/GLM-5.2-REAP50-MLX-4bit"

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 pipenetwork/GLM-5.2-REAP50-MLX-4bit

Run Hermes

hermes

MLX LM

How to use pipenetwork/GLM-5.2-REAP50-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/GLM-5.2-REAP50-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/GLM-5.2-REAP50-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/GLM-5.2-REAP50-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

I don't suppose you could upload the REAP weight before you quantised them

by infinityai - opened 3 days ago

Discussion

infinityai

3 days ago

•

edited 3 days ago

Thank you for making this REAP

I don't suppose you could upload the REAPd 16bit weights before you quantised them, So that we can make more alternative quantisations

Or could you try and quantise them Using this new quantisation method that this person has developed https://github.com/jjang-ai/jangq

https://jangq.ai

From what I can see he is able to quantise them even more possibly reducing it by another half in size while still keeping whilst still keeping the Reasoning capabilities

Thanks

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment