Upload processor

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_vlm.VLMProcessor"
+  },
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "processor_class": "VLMProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "shortest_edge": 336
+  }
+}

processing_vlm.py

@@ -0,0 +1,39 @@
+from typing import Any
+
+from transformers import AutoImageProcessor, AutoProcessor, AutoTokenizer, ProcessorMixin
+
+from .configuration_vlm import VLMConfig
+
+
+class VLMProcessor(ProcessorMixin):
+    attributes: list[str] = ["image_processor", "tokenizer"]
+    image_processor_class: str = "AutoImageProcessor"
+    tokenizer_class: str = "AutoTokenizer"
+
+    def __init__(
+        self,
+        image_processor: AutoImageProcessor = None,
+        tokenizer: AutoTokenizer = None,
+        **kwargs: Any,
+    ):
+        super().__init__(image_processor, tokenizer, **kwargs)
+
+    @classmethod
+    def from_names(cls, image_processor_name: str, tokenizer_name: str, **kwargs: Any):
+        image_processor_args = {
+            k: v for k, v in kwargs.items() if k in ["trust_remote_code", "use_fast"]
+        }
+        tokenizer_args = {
+            k: v
+            for k, v in kwargs.items()
+            if k in ["trust_remote_code", "use_fast", "model_max_length", "padding_side"]
+        }
+
+        tokenizer = AutoTokenizer.from_pretrained(tokenizer_name, **tokenizer_args)
+        image_processor = AutoImageProcessor.from_pretrained(
+            image_processor_name, **image_processor_args
+        )
+        return cls(image_processor=image_processor, tokenizer=tokenizer)
+
+
+AutoProcessor.register(VLMConfig, VLMProcessor)

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_vlm.VLMProcessor"
+  },
+  "processor_class": "VLMProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoProcessor": "processing_vlm.VLMProcessor"
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "processor_class": "VLMProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "torch_dtype": "auto",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}