axolotl-quants
/

Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16 / generation_config.json

winglian's picture

Upload folder using huggingface_hub

eb77729 verified 2 months ago

147 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 200000,
	"eos_token_id": 200001,
	"pad_token_id": 200018,
	"transformers_version": "4.51.0"
	}