Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
vivekvar
/
GSPO-DeepSeek-R1-Distill-Qwen-1.5B
like
2
Text Generation
Safetensors
custom
English
qwen2
reinforcement-learning
reasoning
mathematical-reasoning
gspo
policy-optimization
sequence-level-training
conversational
arxiv:
2507.18071
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
GSPO-DeepSeek-R1-Distill-Qwen-1.5B
7.12 GB
1 contributor
History:
4 commits
vivekvar
Update README.md
3840067
verified
7 months ago
.gitattributes
1.57 kB
Upload folder using huggingface_hub
7 months ago
README.md
5.83 kB
Update README.md
7 months ago
chat_template.jinja
2.25 kB
Upload folder using huggingface_hub
7 months ago
config.json
1.34 kB
Upload folder using huggingface_hub
7 months ago
generation_config.json
181 Bytes
Upload folder using huggingface_hub
7 months ago
model-00001-of-00002.safetensors
5 GB
xet
Upload folder using huggingface_hub
7 months ago
model-00002-of-00002.safetensors
2.11 GB
xet
Upload folder using huggingface_hub
7 months ago
model.safetensors.index.json
27.8 kB
Upload folder using huggingface_hub
7 months ago
special_tokens_map.json
485 Bytes
Upload folder using huggingface_hub
7 months ago
tokenizer.json
11.4 MB
xet
Upload folder using huggingface_hub
7 months ago
tokenizer_config.json
4.49 kB
Upload folder using huggingface_hub
7 months ago
