Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ajagota71
/
toxicity-reward-model-160m-prompt-output-max-margin-1-seed-100-unfrozen-layers-0-pythia-160m
like
0
Safetensors
gpt_neox
Model card
Files
Files and versions
Community
main
toxicity-reward-model-160m-prompt-output-max-margin-1-seed-100-unfrozen-layers-0-pythia-160m
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
ajagota71
Upload IRL reward model
6a248c3
verified
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
README.md
Safe
450 Bytes
Upload IRL reward model
about 1 month ago
config.json
Safe
757 Bytes
Upload IRL reward model
about 1 month ago
config.yaml
Safe
1.41 kB
Upload IRL reward model
about 1 month ago
generation_config.json
111 Bytes
Upload IRL reward model
about 1 month ago
model.safetensors
Safe
649 MB
LFS
Upload IRL reward model
about 1 month ago
reward_model_config.json
Safe
106 Bytes
Upload IRL reward model
about 1 month ago
special_tokens_map.json
Safe
473 Bytes
Upload IRL reward model
about 1 month ago
tokenizer.json
Safe
3.56 MB
Upload IRL reward model
about 1 month ago
tokenizer_config.json
4.88 kB
Upload IRL reward model
about 1 month ago
v_head.pt
Safe
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
4.25 kB
LFS
Upload IRL reward model
about 1 month ago