Upload folder using huggingface_hub

README.md

@@ -26,6 +26,7 @@ Table is an effective way to represent structured data in scientific publication
 
 ## Changelog
 Tips: Current version of StructEqTable is able to process table images from scientific documents such as arXiv, Scihub papers. Times New Roman And Songti(宋体) are main fonts used in table image, other fonts may decrease the accuracy of the model's output.
+- **[2024/8/22] 🔥 We have released our [latest model](https://huggingface.co/U4R/StructTable-base/tree/v0.2), fine-tuned on the DocGenome dataset. This version features improved inference speed and robustness, achieved through data augmentation and reduced image token num.** 
 - [2024/8/08] 🔥 We have released the TensorRT accelerated version, which only takes about 1 second for most images on GPU A100. Please follow the tutorial to install the environment and compile the model weights.
 - [2024/7/30] We have released the first version of StructEqTable. 
 

config.json

@@ -20,7 +20,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.39.1",
   "use_cache": false,
   "vision_config": {
     "attention_dropout": 0.2,

generation_config.json

@@ -3,6 +3,6 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.39.1",
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66baeb5e3b8e13f7e30cdf998c6724af7a97e8a2a3c78ece70666b6e2af278ce
+oid sha256:85661216f7547cba62312829bff47755d12907ea49ebb49dad65ade6ebf64706
 size 1294046176

preprocessor_config.json

@@ -3,7 +3,7 @@
   "do_normalize": true,
   "image_processor_type": "Pix2StructImageProcessor",
   "is_vqa": false,
-  "max_patches": 4096,
+  "max_patches": 2048,
   "patch_size": {
     "height": 16,
     "width": 16