Metin
/

LLaMA-3-8B-Math-Majority-Vote-GRPO

Text Generation

text-generation-inference

test-time-reinforcement-learning

Model card Files Files and versions Community

LLaMA-3-8B-Math-Majority-Vote-GRPO / generation_config.json

Metin's picture

Trained with Unsloth

5bcefe6 verified about 1 month ago

history blame contribute delete

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"
	}