Upload processor

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + ' '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '
+' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '
+' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

processor_config.json

@@ -0,0 +1,177 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_grid_pinpoints": [
+      [
+        384,
+        384
+      ],
+      [
+        384,
+        768
+      ],
+      [
+        384,
+        1152
+      ],
+      [
+        384,
+        1536
+      ],
+      [
+        384,
+        1920
+      ],
+      [
+        384,
+        2304
+      ],
+      [
+        768,
+        384
+      ],
+      [
+        768,
+        768
+      ],
+      [
+        768,
+        1152
+      ],
+      [
+        768,
+        1536
+      ],
+      [
+        768,
+        1920
+      ],
+      [
+        768,
+        2304
+      ],
+      [
+        1152,
+        384
+      ],
+      [
+        1152,
+        768
+      ],
+      [
+        1152,
+        1152
+      ],
+      [
+        1152,
+        1536
+      ],
+      [
+        1152,
+        1920
+      ],
+      [
+        1152,
+        2304
+      ],
+      [
+        1536,
+        384
+      ],
+      [
+        1536,
+        768
+      ],
+      [
+        1536,
+        1152
+      ],
+      [
+        1536,
+        1536
+      ],
+      [
+        1536,
+        1920
+      ],
+      [
+        1536,
+        2304
+      ],
+      [
+        1920,
+        384
+      ],
+      [
+        1920,
+        768
+      ],
+      [
+        1920,
+        1152
+      ],
+      [
+        1920,
+        1536
+      ],
+      [
+        1920,
+        1920
+      ],
+      [
+        1920,
+        2304
+      ],
+      [
+        2304,
+        384
+      ],
+      [
+        2304,
+        768
+      ],
+      [
+        2304,
+        1152
+      ],
+      [
+        2304,
+        1536
+      ],
+      [
+        2304,
+        1920
+      ],
+      [
+        2304,
+        2304
+      ]
+    ],
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "LlavaOnevisionImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 384,
+      "width": 384
+    }
+  },
+  "image_token": "<image>",
+  "num_additional_image_tokens": 0,
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "full"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c444ca8e2127f1074a2cfec39e437fdc909de7b4f3713f91af2c4a9d1fdf9fe9
+size 11418630

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "max_length": null,
+  "model_max_length": 32768,
+  "model_specific_special_tokens": {},
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}