Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
LichengLiu03
/
Qwen2.5-3B-UFO
like
2
Text Generation
Transformers
Safetensors
qwen2
qwen2.5
ppo
rlhf
metamath
math
reasoning
verl
conversational
text-generation-inference
arxiv:
2507.14295
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
main
Qwen2.5-3B-UFO
Ctrl+K
Ctrl+K
2 contributors
History:
8 commits
LichengLiu03
nielsr
HF Staff
Improve model card: Add detailed framework and results sections (
#2
)
555fe4c
verified
22 days ago
.gitattributes
Safe
1.57 kB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
README.md
9.17 kB
Improve model card: Add detailed framework and results sections (#2)
22 days ago
added_tokens.json
Safe
605 Bytes
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
chat_template.jinja
Safe
2.51 kB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
config.json
Safe
1.5 kB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
generation_config.json
Safe
243 Bytes
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
merges.txt
Safe
1.67 MB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
model-00001-of-00002.safetensors
Safe
4.96 GB
LFS
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
model-00002-of-00002.safetensors
Safe
1.21 GB
LFS
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
model.safetensors.index.json
Safe
35.6 kB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
special_tokens_map.json
Safe
613 Bytes
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
tokenizer.json
Safe
11.4 MB
LFS
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
tokenizer_config.json
Safe
4.69 kB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago
vocab.json
Safe
2.78 MB
Upload Qwen2.5-3B-PPO-MetaMath full model (200 steps)
about 1 month ago