Hugging Face's logo

mratsim
/
MiniMax-M2.1-FP8-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
10
MiniMax-M2.1-FP8-INT4-AWQ

Commit History

  1. mention VRAM cost of BF16

    mratsim
    Verified signature
    5b18eb5

  2. remove -FP8 in model name

    mratsim
    Verified signature
    7d33890

  3. Add mention to mratsim/MiniMax-M2.1-BF16-INT4-AWQ

    mratsim
    Verified signature
    f60e498

  1. Fix Engrish

    mratsim
    Verified signature
    7bde446

  2. typo in script command

    mratsim
    Verified signature
    70f7944

  1. Add repetition_penalty and frequency_penalty suggestion

    mratsim
    Verified signature
    a3aac1b

  1. Update README.md

    mratsim
    Verified signature
    2d8be0e

  2. Update README.md

    mratsim
    Verified signature
    bd78c3a

  3. Update README.md

    mratsim
    Verified signature
    b177683

  4. Add performance figures

    mratsim
    Verified signature
    6a70db0

  5. Update README.md

    mratsim
    Verified signature
    2e6cbf9

  6. Create model card

    mratsim
    Verified signature
    87abc8a

  1. Create calibrate_software_engineer.yaml

    mratsim
    Verified signature
    3c9a12b

  2. Upload folder using huggingface_hub

    mratsim
    Verified signature
    34f3f23

  3. initial commit

    mratsim
    Verified signature
    8d6de6f