Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
rinna
/
bilingual-gpt-neox-4b-instruction-ppo
like
16
Text Generation
Transformers
PyTorch
Safetensors
Anthropic/hh-rlhf
Japanese
English
gpt_neox
text-generation-inference
arxiv:
2203.02155
arxiv:
1707.06347
arxiv:
2404.01657
License:
mit
Model card
Files
Files and versions
Community
1
Train
Deploy
Use in Transformers
main
bilingual-gpt-neox-4b-instruction-ppo
3 contributors
History:
5 commits
keisawada
Update README.md
b770517
verified
about 1 month ago
.gitattributes
1.52 kB
initial commit
9 months ago
README.md
8.39 kB
Update README.md
about 1 month ago
config.json
641 Bytes
update
9 months ago
model.safetensors
7.74 GB
LFS
Adding `safetensors` variant of this model (#1)
9 months ago
pytorch_model.bin
pickle
Detected Pickle imports (4)
"torch.BoolStorage"
,
"collections.OrderedDict"
,
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
7.78 GB
LFS
update
9 months ago
rinna.png
60.3 kB
update
9 months ago
spiece.model
1.34 MB
LFS
update
9 months ago
spiece.vocab
1.16 MB
update
9 months ago
tokenizer_config.json
284 Bytes
update
9 months ago