PrunaAI
/

Llama3-ChatQA-1.5-8B-bnb-4bit-smashed

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Llama3-ChatQA-1.5-8B-bnb-4bit-smashed / generation_config.json

sharpenb's picture

Upload folder using huggingface_hub (#1)

da501b4 verified 6 months ago

143 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": [
	128001,
	128009
	],
	"transformers_version": "4.40.0"
	}