Update tiny models for VideoLlama3Model

.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 +1,40 @@
+
+{%- set identifier = 'im' %}
+{% for message in messages %}
+    {% if add_system_prompt and loop.first and message['role'] != 'system' %}
+        {{- '<|im_start|>system
+You are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help people understand images and videos.<|im_end|>
+' -}}
+    {% endif %}
+    {% if message['role'] == 'stream' %}
+        {% set identifier = 'stream' %}
+    {% else %}
+        {% set identifier = 'im' %}
+    {% endif %}
+    {{- '<|' + identifier + '_start|>' + message['role'] + '
+' -}}
+    {% if message['content'] is string %}
+        {{- message['content'] -}}
+    {% else %}
+        {% for content in message['content'] %}
+            {% if content['type'] == 'text' %}
+                {{- content['text'] -}}
+            {% elif content['type'] == 'image' %}
+                {{- '<|image_pad|>' + '
+' -}}
+            {% elif content['type'] == 'video' %}
+                {{- '<|video_pad|>' + '
+' -}}
+            {% endif %}
+        {% endfor %}
+    {% endif %}
+    {{- '<|' + identifier + '_end|>' -}}
+    {% if identifier != 'stream' %}
+        {{- '
+' -}}
+    {% endif %}
+{% endfor %}
+{% if add_generation_prompt %}
+    {{- '<|im_start|>assistant
+' -}}
+{% endif %}

config.json

@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "VideoLlama3Model"
+  ],
+  "dtype": "float32",
+  "image_token_id": 3,
+  "model_type": "video_llama_3",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 512,
+    "max_window_layers": 3,
+    "model_type": "qwen2",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151665
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "use_token_compression": true,
+  "video_token_id": 4,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_norm_eps": 1e-06,
+    "model_type": "video_llama_3_vision",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 14
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3934ffd0dae28c025623c9518d78ede68c509111f6a7f2538b463be8a6d89b37
+size 19627256

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VideoLlama3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 1,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 3211264,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 1
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "VideoLlama3Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_frames": 180,
+  "merge_size": 2,
+  "min_frames": 4,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": true,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 12544
+  },
+  "temporal_patch_size": 1,
+  "use_token_compression": true,
+  "video_processor_type": "VideoLlama3VideoProcessor"
+}