Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
pathcosmos
/
EVAFRILL-Mo-3B
like
1
Text Generation
PyTorch
Safetensors
6 datasets
Korean
English
evafrill-mo
mamba2
hybrid
transformer
korean
from-scratch
dpo
slerp
orpo
nemotron-h
conversational
Eval Results (legacy)
arxiv:
2504.03624
License:
mit
Model card
Files
Files and versions
xet
Community
main
EVAFRILL-Mo-3B
/
orpo
Ctrl+K
Ctrl+K
3 contributors
History:
2 commits
pathcosmos
Upload orpo/README.md with huggingface_hub
fc1a997
verified
6 days ago
README.md
Safe
1.58 kB
Upload orpo/README.md with huggingface_hub
6 days ago
config.json
Safe
694 Bytes
Upload folder using huggingface_hub
6 days ago
lora_weights.pt
Safe
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
,
"collections.OrderedDict"
What is a pickle import?
42.9 MB
xet
Upload folder using huggingface_hub
6 days ago
model.safetensors
Safe
6.3 GB
xet
Upload folder using huggingface_hub
6 days ago
tokenizer.json
Safe
4.24 MB
Upload folder using huggingface_hub
6 days ago
