Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Dongwei
/
DeepSeek-R1-Distill-Qwen-7B-GRPO_Math
like
0
Text Generation
Transformers
Safetensors
DigitalLearningGmbH/MATH-lighteval
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2402.03300
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
6c50d3f
DeepSeek-R1-Distill-Qwen-7B-GRPO_Math
/
generation_config.json
Dongwei
Model save
6c50d3f
verified
12 days ago
raw
Copy download link
history
blame
Safe
186 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
151646
,
"do_sample"
:
true
,
"eos_token_id"
:
151643
,
"temperature"
:
0.6
,
"top_p"
:
0.95
,
"transformers_version"
:
"4.49.0.dev0"
}