ykarout
/

RPT-DeepSeek-R1-0528-Qwen3-8B

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

RPT-DeepSeek-R1-0528-Qwen3-8B / generation_config.json

ykarout's picture

GRPO fine-tuned DeepSeek-R1-Qwen3-8B for next token prediction according to paper https://huggingface.co/papers/2506.08007

251e747 verified 19 days ago

history blame contribute delete

143 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 151643,
	"eos_token_id": 151645,
	"transformers_version": "4.52.4",
	"use_cache": false
	}