mlgawd
/

U3-3-int4_v2

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

U3-3-int4_v2 / generation_config.json

mlgawd's picture

Upload LlamaForCausalLM

20ac38e verified about 1 month ago

143 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128003,
	"transformers_version": "4.47.1",
	"use_cache": false
	}