Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
lomahony
/
pythia-1.4b-helpful-dpo
like
0
Text Generation
Transformers
PyTorch
Anthropic/hh-rlhf
English
gpt_neox
causal-lm
pythia
text-generation-inference
arxiv:
2101.00027
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
3db92c6
pythia-1.4b-helpful-dpo
5.66 GB
1 contributor
History:
2 commits
lomahony
Upload policy.pt
3db92c6
verified
almost 2 years ago
.gitattributes
Safe
1.52 kB
initial commit
almost 2 years ago
policy.pt
pickle
Detected Pickle imports (5)
"torch._utils._rebuild_tensor_v2"
,
"torch.Tensor"
,
"torch._tensor._rebuild_from_type_v2"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
How to fix it?
5.66 GB
xet
Upload policy.pt
almost 2 years ago