humbleakh
/

qwen2.5-vl-3b-8bit-chain-of-zoom

image-text-to-text

vision-language-model

8-bit precision

super-resolution

Eval Results (legacy)

Model card Files Files and versions

qwen2.5-vl-3b-8bit-chain-of-zoom / config.json

humbleakh's picture

Upload VLM model with 8-bit quantization for Chain-of-Zoom

7322441 verified 12 months ago

history blame contribute delete

220 Bytes

	{
	"model_type": "qwen2vl",
	"quantization": "8-bit",
	"architectures": [
	"Qwen2VLForConditionalGeneration"
	],
	"torch_dtype": "bfloat16",
	"precision": "8-bit",
	"base_model": "Qwen/Qwen2.5-VL-3B-Instruct"
	}