solidrust
/

Hermes-3-Llama-3.1-8B-lorablated-AWQ-preview

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Hermes-3-Llama-3.1-8B-lorablated-AWQ-preview / generation_config.json

Suparious's picture

Upload quantized AWQ model

bbcd67d verified 4 months ago

142 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": 128040,
	"transformers_version": "4.44.2"
	}