Upload 6 files

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/siglip2-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: siglip2-finetuned-marathi-sign-language
+  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. -->
+
+# siglip2-finetuned-marathi-sign-language
+
+This model is a fine-tuned version of [google/siglip2-base-patch16-224](https://huggingface.co/google/siglip2-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0006
+- Model Preparation Time: 0.0057
+- Accuracy: 0.9997
+
+## 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: 2e-06
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:--------:|
+| 1.4439        | 1.0   | 940  | 0.0090          | 0.0057                 | 0.9980   |
+| 0.0052        | 2.0   | 1880 | 0.0035          | 0.0057                 | 0.9993   |
+| 0.0031        | 3.0   | 2820 | 0.0016          | 0.0057                 | 0.9997   |
+| 0.001         | 4.0   | 3760 | 0.0010          | 0.0057                 | 0.9997   |
+| 0.0007        | 5.0   | 4700 | 0.0013          | 0.0057                 | 0.9997   |
+| 0.0005        | 6.0   | 5640 | 0.0006          | 0.0057                 | 0.9997   |
+
+
+### Framework versions
+
+- Transformers 4.52.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.1
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,128 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "\u0905",
+    "1": "\u0906",
+    "10": "\u0915",
+    "11": "\u0915\u094d\u0937",
+    "12": "\u0916",
+    "13": "\u0917",
+    "14": "\u0918",
+    "15": "\u091a",
+    "16": "\u091b",
+    "17": "\u091c",
+    "18": "\u091c\u094d\u091e",
+    "19": "\u091d",
+    "2": "\u0907",
+    "20": "\u091f",
+    "21": "\u0920",
+    "22": "\u0921",
+    "23": "\u0922",
+    "24": "\u0923",
+    "25": "\u0924",
+    "26": "\u0925",
+    "27": "\u0926",
+    "28": "\u0927",
+    "29": "\u0928",
+    "3": "\u0908",
+    "30": "\u092a",
+    "31": "\u092b",
+    "32": "\u092c",
+    "33": "\u092d",
+    "34": "\u092e",
+    "35": "\u092f",
+    "36": "\u0930",
+    "37": "\u0932",
+    "38": "\u0933",
+    "39": "\u0935",
+    "4": "\u0909",
+    "40": "\u0936",
+    "41": "\u0938",
+    "42": "\u0939",
+    "5": "\u090a",
+    "6": "\u090f",
+    "7": "\u0910",
+    "8": "\u0913",
+    "9": "\u0914"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "\u0905": "0",
+    "\u0906": "1",
+    "\u0907": "2",
+    "\u0908": "3",
+    "\u0909": "4",
+    "\u090a": "5",
+    "\u090f": "6",
+    "\u0910": "7",
+    "\u0913": "8",
+    "\u0914": "9",
+    "\u0915": "10",
+    "\u0915\u094d\u0937": "11",
+    "\u0916": "12",
+    "\u0917": "13",
+    "\u0918": "14",
+    "\u091a": "15",
+    "\u091b": "16",
+    "\u091c": "17",
+    "\u091c\u094d\u091e": "18",
+    "\u091d": "19",
+    "\u091f": "20",
+    "\u0920": "21",
+    "\u0921": "22",
+    "\u0922": "23",
+    "\u0923": "24",
+    "\u0924": "25",
+    "\u0925": "26",
+    "\u0926": "27",
+    "\u0927": "28",
+    "\u0928": "29",
+    "\u092a": "30",
+    "\u092b": "31",
+    "\u092c": "32",
+    "\u092d": "33",
+    "\u092e": "34",
+    "\u092f": "35",
+    "\u0930": "36",
+    "\u0932": "37",
+    "\u0933": "38",
+    "\u0935": "39",
+    "\u0936": "40",
+    "\u0938": "41",
+    "\u0939": "42"
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cad3848229d1ed53627064836e23ed7ce1eae10adbc7cfe64ec28e65017abc5
+size 371694116

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744c26b953c566e5bbf83b4d41331c7b3911c8d52426a923c75dbcac7fb7089a
+size 5240