Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
FutureMa
/
Qwen2.5-7B-Instruct-GRPO-Math
like
0
Text Generation
Transformers
Safetensors
AI-MO/NuminaMath-TIR
English
qwen2.5
grpo
rlhf
math
reasoning
ms-swift
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Qwen2.5-7B-Instruct-GRPO-Math
/
additional_config.json
FutureMa
Upload GRPO fine-tuned Qwen2.5-7B-Instruct model
bc4cc58
verified
about 1 month ago
raw
Copy download link
history
blame
contribute
delete
Safe
67 Bytes
{
"lora_dtype"
:
null
,
"lorap_lr_ratio"
:
null
,
"lorap_emb_lr"
:
1e-06
}