kernelpool's picture
Add files using upload-large-folder tool
4b11a2d verified
metadata
pipeline_tag: text-generation
license: other
license_name: modified-mit
license_link: https://github.com/MiniMax-AI/MiniMax-M2.5/blob/main/LICENSE
library_name: mlx
base_model: MiniMaxAI/MiniMax-M2.5
tags:
  - mlx

catalystsec/MiniMax-M2.5-4bit-DWQ

This model was quantized to 4-bit using DWQ with mlx-lm version 0.30.7.

Parameter Value
DWQ learning rate 3e-7
Batch size 1
Dataset allenai/tulu-3-sft-mixture
Initial validation loss 0.077
Final validation loss 0.053
Relative KL reduction ≈31 %
Tokens processed ≈1.11 M

Perplexity

Evaluated on 210 samples of 512 tokens from the default mlx-lm calibration data.

Model Perplexity
3-bit 7.802
3-bit DWQ 7.434
4-bit 6.581
4-bit DWQ 6.431

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("catalystsec/MiniMax-M2.5-4bit-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)