Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Boxed-AIMO2
/
DeepSeek-R1-Distill-Qwen-14B-INT8-W8A8
like
0
Follow
Boxed-AIMO2
4
Safetensors
qwen2
8-bit precision
compressed-tensors
Model card
Files
Files and versions
Community
3911161
DeepSeek-R1-Distill-Qwen-14B-INT8-W8A8
/
recipe.yaml
rd211
Upload folder using huggingface_hub
3911161
verified
14 days ago
raw
Copy download link
history
blame
Safe
170 Bytes
DEFAULT_stage:
DEFAULT_modifiers:
SmoothQuantModifier:
{
smoothing_strength:
0.8
}
GPTQModifier:
scheme:
W8A8
targets:
Linear
ignore:
[
lm_head
]