Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
saricles
/
MiniMax-M2.5-REAP-172B-A10B-NVFP4-GB10
like
18
Text Generation
Transformers
Safetensors
English
Chinese
minimax_m2
minimax
nvfp4
4-bit precision
quantized
compressed-tensors
vllm
DGX-Spark
GB10
MoE
REAP
conversational
custom_code
8-bit precision
arxiv:
2510.13999
License:
mit
Model card
Files
Files and versions
xet
Community
3
Deploy
Use this model
main
MiniMax-M2.5-REAP-172B-A10B-NVFP4-GB10
/
generation_config.json
saricles
MiniMax M2.5 REAP 172B NVFP4 quantization - all layers including self_attn
ab78cfb
verified
about 1 month ago
raw
Copy download link
history
blame
contribute
delete
Safe
111 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"4.57.6"
}