Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ tags:
|
|
| 13 |
library_name: transformers
|
| 14 |
---
|
| 15 |
|
| 16 |
-
This is a GPTQ-quantized 4-bit version of [huihui-ai/
|
| 17 |
|
| 18 |
This is just the quantification test for GPTQ, with only one dataset: "gptqmodel is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm.".
|
| 19 |
If you need your own dataset, please contact us: support@huihui.ai
|
|
@@ -37,7 +37,7 @@ model = Qwen2VLForConditionalGeneration.from_pretrained(
|
|
| 37 |
)
|
| 38 |
|
| 39 |
# default processer
|
| 40 |
-
processor = AutoProcessor.from_pretrained("huihui-ai/QVQ-72B-Preview-abliterated")
|
| 41 |
|
| 42 |
# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
|
| 43 |
# min_pixels = 256*28*28
|
|
|
|
| 13 |
library_name: transformers
|
| 14 |
---
|
| 15 |
|
| 16 |
+
This is a GPTQ-quantized 4-bit version of [huihui-ai/QVQ-72B-Preview-abliterated](https://huggingface.co/huihui-ai/QVQ-72B-Preview-abliterated).
|
| 17 |
|
| 18 |
This is just the quantification test for GPTQ, with only one dataset: "gptqmodel is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm.".
|
| 19 |
If you need your own dataset, please contact us: support@huihui.ai
|
|
|
|
| 37 |
)
|
| 38 |
|
| 39 |
# default processer
|
| 40 |
+
processor = AutoProcessor.from_pretrained("huihui-ai/QVQ-72B-Preview-abliterated-GPTQ-Int4")
|
| 41 |
|
| 42 |
# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
|
| 43 |
# min_pixels = 256*28*28
|