Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
donut
document-parsing
lhdn
ebc
Instructions to use acceler-technology/dev-lhdn-parse-donut-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use acceler-technology/dev-lhdn-parse-donut-model with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="acceler-technology/dev-lhdn-parse-donut-model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("acceler-technology/dev-lhdn-parse-donut-model") model = AutoModelForMultimodalLM.from_pretrained("acceler-technology/dev-lhdn-parse-donut-model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +4 -4
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -81,7 +81,7 @@
|
|
| 81 |
"tokenizer_class": null,
|
| 82 |
"top_k": 50,
|
| 83 |
"top_p": 1.0,
|
| 84 |
-
"torch_dtype":
|
| 85 |
"torchscript": false,
|
| 86 |
"typical_p": 1.0,
|
| 87 |
"use_bfloat16": false,
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
},
|
| 128 |
"image_size": [
|
| 129 |
700,
|
| 130 |
-
|
| 131 |
],
|
| 132 |
"initializer_range": 0.02,
|
| 133 |
"is_decoder": false,
|
|
@@ -178,7 +178,7 @@
|
|
| 178 |
"tokenizer_class": null,
|
| 179 |
"top_k": 50,
|
| 180 |
"top_p": 1.0,
|
| 181 |
-
"torch_dtype":
|
| 182 |
"torchscript": false,
|
| 183 |
"typical_p": 1.0,
|
| 184 |
"use_absolute_embeddings": false,
|
|
@@ -190,5 +190,5 @@
|
|
| 190 |
"pad_token_id": 1,
|
| 191 |
"tie_word_embeddings": false,
|
| 192 |
"torch_dtype": "float32",
|
| 193 |
-
"transformers_version": "4.
|
| 194 |
}
|
|
|
|
| 81 |
"tokenizer_class": null,
|
| 82 |
"top_k": 50,
|
| 83 |
"top_p": 1.0,
|
| 84 |
+
"torch_dtype": null,
|
| 85 |
"torchscript": false,
|
| 86 |
"typical_p": 1.0,
|
| 87 |
"use_bfloat16": false,
|
|
|
|
| 127 |
},
|
| 128 |
"image_size": [
|
| 129 |
700,
|
| 130 |
+
2400
|
| 131 |
],
|
| 132 |
"initializer_range": 0.02,
|
| 133 |
"is_decoder": false,
|
|
|
|
| 178 |
"tokenizer_class": null,
|
| 179 |
"top_k": 50,
|
| 180 |
"top_p": 1.0,
|
| 181 |
+
"torch_dtype": null,
|
| 182 |
"torchscript": false,
|
| 183 |
"typical_p": 1.0,
|
| 184 |
"use_absolute_embeddings": false,
|
|
|
|
| 190 |
"pad_token_id": 1,
|
| 191 |
"tie_word_embeddings": false,
|
| 192 |
"torch_dtype": "float32",
|
| 193 |
+
"transformers_version": "4.47.0"
|
| 194 |
}
|
generation_config.json
CHANGED
|
@@ -5,5 +5,5 @@
|
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"max_length": 1000,
|
| 7 |
"pad_token_id": 1,
|
| 8 |
-
"transformers_version": "4.
|
| 9 |
}
|
|
|
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"max_length": 1000,
|
| 7 |
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.47.0"
|
| 9 |
}
|