Update tiny models for Qwen2_5OmniThinkerForConditionalGeneration

.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 +1,7 @@
+{% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,93 @@
+{
+  "architectures": [
+    "Qwen2_5OmniThinkerForConditionalGeneration"
+  ],
+  "audio_config": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "attention_dropout": 0.0,
+    "d_model": 32,
+    "dropout": 0.0,
+    "encoder_attention_heads": 4,
+    "encoder_ffn_dim": 32,
+    "encoder_layers": 2,
+    "initializer_range": 0.02,
+    "max_source_positions": 1500,
+    "model_type": "qwen2_5_omni_audio_encoder",
+    "n_window": 100,
+    "num_mel_bins": 20,
+    "output_dim": 32,
+    "scale_embedding": false
+  },
+  "audio_end_token_id": 5,
+  "audio_start_token_id": 4,
+  "audio_token_index": 1,
+  "dtype": "float32",
+  "image_token_index": 2,
+  "initializer_range": 0.02,
+  "model_type": "qwen2_5_omni_thinker",
+  "position_id_per_seconds": 25,
+  "seconds_per_chunk": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 1024,
+    "max_window_layers": 3,
+    "model_type": "qwen2_5_omni_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_section": [
+        1,
+        1,
+        2
+      ],
+      "rope_theta": 1000000.0,
+      "rope_type": "default",
+      "type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151665
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "user_token_id": 6,
+  "video_token_index": 3,
+  "vision_config": {
+    "depth": 2,
+    "embed_dim": 32,
+    "fullatt_block_indexes": [
+      0
+    ],
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 24,
+    "mlp_ratio": 4,
+    "model_type": "qwen2_5_omni_vision_encoder",
+    "num_heads": 4,
+    "out_hidden_size": 32,
+    "patch_size": 14,
+    "spatial_merge_size": 1,
+    "temporal_patch_size": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 8,
+  "vision_start_token_id": 7
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 151643,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc366362f6515f0c9365f874b1262c589d87d3557dedc25910efe3c0f7af2126
+size 39179728

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "chunk_length": 300,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 14,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "temporal_patch_size": 2
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab7a851e5c63d5fafbfdac72e3b4a8d08613f6bbb06ee39036fdf870ef59c93
+size 11421866

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_token": "<|AUDIO|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|IMAGE|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_bos|>",
+    "audio_eos_token": "<|audio_eos|>",
+    "audio_token": "<|AUDIO|>",
+    "image_token": "<|IMAGE|>",
+    "video_token": "<|VIDEO|>",
+    "vision_bos_token": "<|vision_bos|>",
+    "vision_eos_token": "<|vision_eos|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5OmniProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|VIDEO|>",
+  "vision_bos_token": "<|vision_bos|>",
+  "vision_eos_token": "<|vision_eos|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "chunk_length": 300,
+  "dither": 0.0,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "feature_size": 128,
+  "hop_length": 160,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_metadata": false,
+  "sampling_rate": 16000,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}