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
/
scripts
133 kB
Ctrl+K
Ctrl+K
3 contributors
History:
1 commit
pathcosmos
Upload folder using huggingface_hub
29fc577
verified
6 days ago
dpo.py
Safe
17 kB
Upload folder using huggingface_hub
6 days ago
evafrill_eval.py
Safe
25.8 kB
Upload folder using huggingface_hub
6 days ago
generate_repetition_preference.py
Safe
18.4 kB
Upload folder using huggingface_hub
6 days ago
lora.py
Safe
8.33 kB
Upload folder using huggingface_hub
6 days ago
merge_checkpoints.py
Safe
6.31 kB
Upload folder using huggingface_hub
6 days ago
orpo_native.py
Safe
26 kB
Upload folder using huggingface_hub
6 days ago
sft.py
Safe
31.6 kB
Upload folder using huggingface_hub
6 days ago
