Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ library_name: transformers
|
|
13 |
|
14 |
# olmOCR-7B-0725-FP8
|
15 |
|
16 |
-
Quantized to FP8 Version, using llmcompressor.
|
17 |
|
18 |
This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the
|
19 |
[olmOCR-mix-0225](https://huggingface.co/datasets/allenai/olmOCR-mix-0225) dataset.
|
@@ -30,7 +30,7 @@ at scale.
|
|
30 |
|
31 |
## Usage
|
32 |
|
33 |
-
This model expects as input a single document image, rendered such that the longest dimension is
|
34 |
|
35 |
The prompt must then contain the additional metadata from the document, and the easiest way to generate this
|
36 |
is to use the methods provided by the [olmOCR toolkit](https://github.com/allenai/olmocr).
|
|
|
13 |
|
14 |
# olmOCR-7B-0725-FP8
|
15 |
|
16 |
+
Quantized to FP8 Version of [olmOCR-7B-0725](https://huggingface.co/allenai/olmOCR-7B-0725), using llmcompressor.
|
17 |
|
18 |
This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the
|
19 |
[olmOCR-mix-0225](https://huggingface.co/datasets/allenai/olmOCR-mix-0225) dataset.
|
|
|
30 |
|
31 |
## Usage
|
32 |
|
33 |
+
This model expects as input a single document image, rendered such that the longest dimension is 1288 pixels.
|
34 |
|
35 |
The prompt must then contain the additional metadata from the document, and the easiest way to generate this
|
36 |
is to use the methods provided by the [olmOCR toolkit](https://github.com/allenai/olmocr).
|