MiniMax M2 DWQ
Collection
2 items • Updated • 1
How to use from
PiConfigure 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": "catalystsec/MiniMax-M2-4bit-DWQ"
}
]
}
}
}Run Pi
# Start Pi in your project directory:
piQuick Links
catalystsec/MiniMax-M2-4bit-DWQ
This model was quantized to 4-bit using DWQ with mlx-lm version 0.28.4.
| Parameter | Value |
|---|---|
| DWQ learning rate | 3e-7 |
| Batch size | 1 |
| Dataset | allenai/tulu-3-sft-mixture |
| Initial validation loss | 0.069 |
| Final validation loss | 0.047 |
| Relative KL reduction | ≈32 % |
| Tokens processed | ≈1.09 M |
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("catalystsec/MiniMax-M2-4bit-DWQ")
prompt = "hello"
if tokenizer.chat_template is not None:
prompt = tokenizer.apply_chat_template(
[{"role": "user", "content": prompt}],
add_generation_prompt=True,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
print(response)
- Downloads last month
- 36
Model size
229B params
Tensor type
BF16
·
U32 ·
F32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for catalystsec/MiniMax-M2-4bit-DWQ
Base model
MiniMaxAI/MiniMax-M2
Start the MLX server
# Install MLX LM: uv tool install mlx-lm# Start a local OpenAI-compatible server: mlx_lm.server --model "catalystsec/MiniMax-M2-4bit-DWQ"