Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
psp-dada
/
Qwen2.5-Math-7B-Uni-DPO
like
1
Text Generation
Transformers
Safetensors
psp-dada/Uni-DPO
English
qwen2
bf16
qwen
RLHF
DPO
text-generation-inference
arxiv:
2506.10054
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Qwen2.5-Math-7B-Uni-DPO
15.2 GB
1 contributor
History:
1 commit
psp-dada
first commit
d3f8911
about 22 hours ago
train_results
first commit
about 22 hours ago
.gitattributes
1.63 kB
first commit
about 22 hours ago
.gitignore
19 Bytes
first commit
about 22 hours ago
README.md
5.29 kB
first commit
about 22 hours ago
added_tokens.json
605 Bytes
first commit
about 22 hours ago
config.json
722 Bytes
first commit
about 22 hours ago
generation_config.json
117 Bytes
first commit
about 22 hours ago
merges.txt
1.67 MB
first commit
about 22 hours ago
model-00001-of-00004.safetensors
4.88 GB
xet
first commit
about 22 hours ago
model-00002-of-00004.safetensors
4.93 GB
xet
first commit
about 22 hours ago
model-00003-of-00004.safetensors
4.33 GB
xet
first commit
about 22 hours ago
model-00004-of-00004.safetensors
1.09 GB
xet
first commit
about 22 hours ago
model.safetensors.index.json
27.8 kB
first commit
about 22 hours ago
special_tokens_map.json
534 Bytes
first commit
about 22 hours ago
tokenizer.json
7.03 MB
xet
first commit
about 22 hours ago
tokenizer_config.json
7.33 kB
xet
first commit
about 22 hours ago
training_args.bin
7.99 kB
xet
first commit
about 22 hours ago
vocab.json
2.78 MB
first commit
about 22 hours ago