Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
amd
/
Zebra-Llama-3B-6MLA-22Mamba-DPO
like
0
Follow
AMD
2.17k
Safetensors
HuggingFaceH4/ultrafeedback_binarized
HuggingFaceH4/orca_dpo_pairs
JunxiongWang/llama3-ultrafeedback-armorm
llama
alignment-handbook
Generated from Trainer
arxiv:
2505.17272
arxiv:
2503.11132
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
Zebra-Llama-3B-6MLA-22Mamba-DPO
15.1 GB
3 contributors
History:
15 commits
Mingyuyang-1
Update README.md
3a478a6
verified
3 months ago
.gitattributes
1.52 kB
initial commit
7 months ago
LICENSE
15.6 kB
Upload LICENSE
6 months ago
README.md
13.2 kB
Update README.md
3 months ago
comparison.png
96.5 kB
Upload comparison.png
7 months ago
config.json
928 Bytes
Update config.json
7 months ago
generation_config.json
184 Bytes
Upload folder using huggingface_hub
7 months ago
hybrid_config.json
951 Bytes
Update hybrid_config.json
4 months ago
model.safetensors
15.1 GB
xet
Convert weights to .safetensors and remove PyTorch .bin files
3 months ago
special_tokens_map.json
439 Bytes
Upload folder using huggingface_hub
7 months ago
tokenizer.json
9.09 MB
Upload folder using huggingface_hub
7 months ago
tokenizer_config.json
50.9 kB
Upload folder using huggingface_hub
7 months ago
