aiswaryards
/

deepseek1.3B-coder-qlora-finetuned-8bit

Model card Files Files and versions Community

deepseek1.3B-coder-qlora-finetuned-8bit / generation_config.json

aiswaryards's picture

🚀 Uploading full QLoRA 8bit fine-tuned DeepSeek 1.3B model

6e2bb22 verified about 1 month ago

history blame contribute delete

119 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 32013,
	"eos_token_id": 32014,
	"transformers_version": "4.51.3"
	}