Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Resa-Yi
/
DeepScaleR-Trained-from-Scratch-SAE-R1-Distill-Qwen-1.5B-65k
like
0
Follow
Resa
11
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
DeepScaleR-Trained-from-Scratch-SAE-R1-Distill-Qwen-1.5B-65k
1.61 GB
2 contributors
History:
3 commits
farukakgul
add trained-from-scratch saes around ckpt 1000
d4b4907
9 months ago
model.layers.12
add trained-from-scratch saes around ckpt 1000
9 months ago
.gitattributes
Safe
1.52 kB
initial commit
9 months ago
README.md
Safe
31 Bytes
initial commit
9 months ago
config.json
852 Bytes
add trained-from-scratch saes around ckpt 1000
9 months ago
optimizer_0.pt
806 MB
xet
add trained-from-scratch saes around ckpt 1000
9 months ago
rank_0_state.pt
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.LongStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
526 kB
xet
add trained-from-scratch saes around ckpt 1000
9 months ago
state.pt
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
856 Bytes
xet
add trained-from-scratch saes around ckpt 0
9 months ago
