solidrust
/

Vezora-Dolphin-llama-Instruct-8b-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Vezora-Dolphin-llama-Instruct-8b-AWQ / generation_config.json

Ubuntu

adding AWQ model

4c9d3f8 about 2 months ago

raw history blame contribute delete

No virus

164 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": 128001,
	"transformers_version": "4.38.2",
	"use_cache": false
	}