mlx-community
/

Fara-7B-8bit

Image-Text-to-Text

vision-language

8-bit precision

Model card Files Files and versions

Fara-7B-8bit / generation_config.json

axiom-of-choice's picture

axiom-of-choice

Add MLX 8-bit conversion of microsoft/Fara-7B with vision preserved and weight-level fidelity vs bf16

a39db61 verified 10 days ago

History Blame Contribute Delete

214 Bytes

	{
	"bos_token_id": 151643,
	"do_sample": true,
	"eos_token_id": [
	151645,
	151643
	],
	"pad_token_id": 151643,
	"repetition_penalty": 1.05,
	"temperature": 1e-06,
	"transformers_version": "4.52.4"
	}