Update tiny models for CohereCompassVisionModel

.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 @@
+{{ bos_token }}{%- for message in messages %}{%- if message.role == 'system' %}{{- '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{%- if message.content is string %}{{- message.content }}{%- else %}{%- for content in message.content %}{%- if 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|END_OF_TURN_TOKEN|>' }}{%- elif message.role == 'user' %}{{- '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' }}{%- if message.content is string %}{{- message.content }}{%- else %}{%- for content in message.content %}{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}<|VISION_START|><|IMAGE_PAD|><|VISION_END|>{%- elif content.type == 'video' or 'video' in content %}<|VISION_START|><|VIDEO_PAD|><|VISION_END|>{%- elif 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|END_OF_TURN_TOKEN|>' }}{%- elif message.role == 'assistant' or message.role == 'chatbot' %}{{- '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{%- if message.content is string %}{{- message.content }}{%- else %}{%- for content in message.content %}{%- if 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|END_OF_TURN_TOKEN|>' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{%- endif %}

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "CohereCompassVisionModel"
+  ],
+  "deepstack_visual_indexes": [
+    0
+  ],
+  "depth": 2,
+  "dtype": "float32",
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "in_channels": 3,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "model_type": "cohere_compass_vision",
+  "num_heads": 4,
+  "num_position_embeddings": 2304,
+  "out_hidden_size": 32,
+  "patch_size": 16,
+  "spatial_merge_size": 2,
+  "temporal_patch_size": 2,
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb91867848c702f54e6ad6771f2308dccec0d062a3309c17615db1aaa5d4c84
+size 729896

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "CohereCompassImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 2,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4594953eca27aa1122252e8a61a91a5b4941c92aba78d3811c8fe9b1b95d7f68
+size 19550475

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS>",
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "errors": "replace",
+  "image_token": "<|IMAGE_PAD|>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "mask_token": "<MASK_TOKEN>",
+  "max_pixels": 3868706,
+  "min_pixels": 16384,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "image_token": "<|IMAGE_PAD|>",
+    "video_token": "<|VIDEO_PAD|>",
+    "vision_end_token": "<|VISION_END|>",
+    "vision_start_token": "<|VISION_START|>"
+  },
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "processor_class": "CohereCompassProcessor",
+  "sep_token": "<SEP>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "video_token": "<|VIDEO_PAD|>",
+  "vision_end_token": "<|VISION_END|>",
+  "vision_start_token": "<|VISION_START|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_processor_type": "CohereCompassVideoProcessor"
+}