Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nm-testing
/
Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16-sgl
like
0
Follow
NM Testing
88
Safetensors
custom_code
Model card
Files
Files and versions
xet
Community
main
Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16-sgl
4.09 GB
1 contributor
History:
2 commits
RelaxingSnorlax
Upload processed model with renamed layers and architecture
83009a3
verified
26 days ago
.gitattributes
Safe
1.52 kB
initial commit
26 days ago
config.json
1.37 kB
Upload processed model with renamed layers and architecture
26 days ago
eagle3.py
Safe
19.6 kB
Upload processed model with renamed layers and architecture
26 days ago
generation_config.json
Safe
69 Bytes
Upload processed model with renamed layers and architecture
26 days ago
model.safetensors
4.09 GB
xet
Upload processed model with renamed layers and architecture
26 days ago
