Hugging Face's logo

mratsim
/
MiniMax-M2.5-BF16-INT4-AWQ

Text Generation
Safetensors
llm-compressor
minimax_m2
fp8
awq
conversational
vllm
code
devops
software engineering
engineer
developer
architect
stem
agent
custom_code
compressed-tensors
Model card Files
xet
 Community
9
MiniMax-M2.5-BF16-INT4-AWQ / README.md

Commit History

  1. Point to M2.5 not M2.1

    mratsim
    Verified signature
    7a81459

  2. Update README: FP8 model, multilingual dataset, Visual showcase

    mratsim
    Verified signature
    32e1ea0

  1. for the BF16 weights are dequantized not copied

    mratsim
    Verified signature
    c27b664

  2. Mention the requant in changelog

    mratsim
    Verified signature
    13d1d69

  3. Upload folder using huggingface_hub

    mratsim
    Verified signature
    5bc26c9

  1. Update README.md

    mratsim
    Verified signature
    8a2d415

  2. Upload folder using huggingface_hub

    mratsim
    Verified signature
    35d1eb0