Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
arlineka
/
manbasya_2x7b_MOE
like
0
Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
Inference Endpoints
4-bit precision
awq
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
manbasya_2x7b_MOE
/
quant_config.json
arlineka
Upload quant_config.json with huggingface_hub
4c09c6a
verified
7 months ago
raw
Copy download link
history
blame
contribute
delete
No virus
144 Bytes
{
"zero_point"
:
true
,
"q_group_size"
:
128
,
"w_bit"
:
4
,
"version"
:
"GEMM"
,
"modules_to_not_convert"
:
[
"gate"
]
}