Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Metin
/
LLaMA-3-8B-Math-Majority-Vote-GRPO
like
2
Text Generation
Transformers
Safetensors
English
Turkish
llama
text-generation-inference
unsloth
trl
grpo
test-time-reinforcement-learning
conversational
arxiv:
2504.16084
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
refs/pr/1
LLaMA-3-8B-Math-Majority-Vote-GRPO
/
generation_config.json
Metin
Trained with Unsloth
5bcefe6
verified
9 months ago
raw
Copy download link
history
blame
Safe
169 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
128000
,
"eos_token_id"
:
128009
,
"max_length"
:
8192
,
"pad_token_id"
:
128255
,
"transformers_version"
:
"4.51.3"
}