Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Schrieffer
/
SARM-4B
like
0
Safetensors
llama
reward-model
rlhf
sparse-autoencoder
interpretability
arxiv:
2508.08746
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
SARM-4B
9.11 GB
1 contributor
History:
9 commits
Schrieffer
Update README.md
be1a05c
verified
20 days ago
.gitattributes
Safe
1.52 kB
initial commit
24 days ago
README.md
798 Bytes
Update README.md
20 days ago
config.json
Safe
953 Bytes
Update config.json
20 days ago
model-00001-of-00002.safetensors
Safe
4.98 GB
xet
Initial commit of the reward model
24 days ago
model-00002-of-00002.safetensors
Safe
4.13 GB
xet
Initial commit of the reward model
24 days ago
model.safetensors.index.json
Safe
12.3 kB
Initial commit of the reward model
24 days ago
special_tokens_map.json
Safe
434 Bytes
Add tokenizer
20 days ago
tokenizer.json
Safe
9.09 MB
Add tokenizer
20 days ago
tokenizer_config.json
Safe
55.5 kB
Add tokenizer
20 days ago