Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: ybelkada/pix2struct-base
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+This model is a fine-tuned version of [ybelkada/pix2struct-base](https://huggingface.co/ybelkada/pix2struct-base) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.4.0.dev20240407+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "ybelkada/pix2struct-base",
+  "architectures": [
+    "Pix2StructForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "is_vqa": false,
+  "model_type": "pix2struct",
+  "pad_token_id": 0,
+  "text_config": {
+    "dropout_rate": 0.2,
+    "encoder_hidden_size": 768,
+    "initializer_range": 0.02,
+    "model_type": "pix2struct_text_model"
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "attention_dropout": 0.2,
+    "dropout_rate": 0.2,
+    "hidden_dropout_prob": 0.2,
+    "initializer_range": 0.02,
+    "layer_norm_bias": false,
+    "model_type": "pix2struct_vision_model",
+    "num_channels": 3,
+    "patch_size": 16,
+    "projection_dim": 768
+  }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883695c5a94c86307ede9fe34c770b79d8160bb5055e68bafc00989a7276495d
+size 1129177976

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c471c63cfe1296219a7ce8be7e2911a24132adb7e1b6df8d5b04a764777318ad
+size 4920