Ali7538
/

EPFLLaMA_MCQA_Quantized

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

EPFLLaMA_MCQA_Quantized / generation_config.json

Ali7538's picture

EPFLLaMA specialized for MCQA, int8 quantization

9f8ec0c verified almost 2 years ago

history blame contribute delete

124 Bytes

	{
	"bos_token_id": 1,
	"eos_token_id": 2,
	"max_length": 2048,
	"pad_token_id": 0,
	"transformers_version": "4.41.1"
	}