Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Vezora
/
QwQ-32B-Preview-fp8-W8A16
like
0
Safetensors
qwen2
arxiv:
2411.02355
License:
apache-2.0
Model card
Files
Files and versions
Community
1
435a793
QwQ-32B-Preview-fp8-W8A16
/
recipe.yaml
Vezora
Upload 7 files
435a793
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
134 Bytes
DEFAULT_stage:
DEFAULT_modifiers:
QuantizationModifier:
ignore:
[
lm_head
]
targets:
Linear
scheme:
FP8_DYNAMIC