Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
BioMistral
/
BioMistral-7B-AWQ-QGS128-W4-GEMM
like
3
Follow
BioMistral
63
Text Generation
Transformers
Safetensors
mit-han-lab/pile-val-backup
pubmed
9 languages
mistral
medical
biology
awq
quantization
conversational
text-generation-inference
Inference Endpoints
4-bit precision
arxiv:
2402.10373
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
6739b64
BioMistral-7B-AWQ-QGS128-W4-GEMM
/
quant_config.json
qanastek
Upload 7 files
535d19d
verified
10 months ago
raw
Copy download link
history
blame
Safe
90 Bytes
{
"zero_point"
:
true
,
"q_group_size"
:
128
,
"w_bit"
:
4
,
"version"
:
"GEMM"
}