ecastera
/

eva-dolphin-llama3-8b-spanish

Text Generation

cognitivecomputations/dolphin-2.9-llama3-8b

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

eva-dolphin-llama3-8b-spanish / generation_config.json

ecastera's picture

initial commit

9500476 verified 6 months ago

142 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": 128001,
	"transformers_version": "4.40.0"
	}