Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lomahony
/
eleuther-pythia160m-hh-dpo
like
0
Text Generation
Transformers
PyTorch
Anthropic/hh-rlhf
English
gpt_neox
causal-lm
pythia
text-generation-inference
Inference Endpoints
arxiv:
2305.18290
arxiv:
2101.00027
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
4137f12
eleuther-pythia160m-hh-dpo
1 contributor
History:
2 commits
lomahony
First model version
4137f12
12 months ago
.gitattributes
1.52 kB
initial commit
12 months ago
config.yaml
991 Bytes
First model version
12 months ago
optimizer.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
649 MB
LFS
First model version
12 months ago
policy.pt
pickle
Detected Pickle imports (6)
"torch.FloatStorage"
,
"torch.BoolStorage"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.Tensor"
How to fix it?
700 MB
LFS
First model version
12 months ago
scheduler.pt
pickle
627 Bytes
LFS
First model version
12 months ago