daksh-neo
/

sarvam-30b-quantized

Text Generation

Mixture of Experts

Model card Files Files and versions

sarvam-30b-quantized / generation_config.json

daksh-neo's picture

Upload Sarvam-30B ultra-quantized model (1-bit HQQ, 4.34GB)

7890a94 verified about 1 month ago

history blame contribute delete

112 Bytes

	{
	"_from_model_config": true,
	"eos_token_id": 26,
	"pad_token_id": 0,
	"transformers_version": "4.57.2"
	}