mesolitica
/

malaysian-tinyllama-1.1b-16k-instructions-rag-AWQ

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

malaysian-tinyllama-1.1b-16k-instructions-rag-AWQ / quant_config.json

huseinzol05's picture

Upload quant_config.json with huggingface_hub

021f564 verified 10 months ago

126 Bytes

	{
	"zero_point": true,
	"q_group_size": 128,
	"w_bit": 4,
	"version": "GEMM",
	"modules_to_not_convert": null
	}