Add 4-bit quantized model

.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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|AUDIO|>": 151646,
+  "<|IMAGE|>": 151655,
+  "<|VIDEO|>": 151656,
+  "<|audio_bos|>": 151647,
+  "<|audio_eos|>": 151648,
+  "<|box_end|>": 151649,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|vision_bos|>": 151652,
+  "<|vision_eos|>": 151653,
+  "<|vision_pad|>": 151654
+}

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 +1,567 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "Qwen2_5OmniModel"
+  ],
+  "enable_audio_output": true,
+  "enable_talker": true,
+  "model_type": "qwen2_5_omni",
+  "talker_config": {
+    "_attn_implementation_autoset": true,
+    "architectures": [
+      "Qwen2OmniTalkerForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "audio_end_token_id": 151648,
+    "audio_start_token_id": 151647,
+    "audio_token_index": 151646,
+    "embedding_size": 2048,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "image_token_index": 151655,
+    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 4864,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_omni_talker",
+    "num_attention_heads": 14,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "position_id_per_seconds": 25,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        16,
+        0
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "seconds_per_chunk": 2,
+    "sliding_window": 32768,
+    "spatial_merge_size": 2,
+    "torch_dtype": "float16",
+    "tts_codec_end_token_id": 8294,
+    "tts_codec_mask_token_id": 8296,
+    "tts_codec_pad_token_id": 8292,
+    "tts_codec_start_token_id": 8293,
+    "tts_text_end_token_id": 151861,
+    "tts_text_pad_token_id": 151859,
+    "tts_text_start_token_id": 151860,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_index": 151656,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vocab_size": 8448
+  },
+  "thinker_config": {
+    "_attn_implementation_autoset": true,
+    "architectures": [
+      "Qwen2OmniNaViTThinkerForConditionalGeneration"
+    ],
+    "audio_config": {
+      "_attn_implementation_autoset": true,
+      "activation_dropout": 0.0,
+      "activation_function": "gelu",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "d_model": 1280,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.0,
+      "early_stopping": false,
+      "encoder_attention_heads": 20,
+      "encoder_ffn_dim": 5120,
+      "encoder_layerdrop": 0.0,
+      "encoder_layers": 32,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_source_positions": 1500,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_audio_encoder",
+      "n_window": 100,
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 32,
+      "num_mel_bins": 128,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_dim": 2048,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "scale_embedding": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "audio_end_token_id": 151648,
+    "audio_start_token_id": 151647,
+    "audio_token_index": 151646,
+    "bos_token_id": 151644,
+    "eos_token_id": 151645,
+    "ignore_index": -100,
+    "image_token_index": 151655,
+    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "model_type": "qwen2_5_omni_thinker",
+    "pad_token_id": 151643,
+    "position_id_per_seconds": 25,
+    "seconds_per_chunk": 2,
+    "text_config": {
+      "_attn_implementation_autoset": false,
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "intermediate_size": 11008,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 32768,
+      "max_window_layers": 70,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_text",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 36,
+      "num_key_value_heads": 2,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "mrope_section": [
+          16,
+          24,
+          24
+        ],
+        "rope_type": "default",
+        "type": "default"
+      },
+      "rope_theta": 1000000.0,
+      "sep_token_id": null,
+      "sliding_window": 32768,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 151936
+    },
+    "torch_dtype": "float16",
+    "user_token_id": 872,
+    "video_token_index": 151656,
+    "vision_config": {
+      "_attn_implementation_autoset": true,
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "depth": 32,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "embed_dim": 1280,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "fullatt_block_indexes": [
+        7,
+        15,
+        23,
+        31
+      ],
+      "hidden_act": "silu",
+      "hidden_size": 1280,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "in_chans": 3,
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "intermediate_size": 3420,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_vision_encoder",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_heads": 16,
+      "num_return_sequences": 1,
+      "out_hidden_size": 2048,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 14,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "tokens_per_second": 25,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "window_size": 112
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654
+  },
+  "token2wav_config": {
+    "_attn_implementation_autoset": true,
+    "bigvgan_config": {
+      "_attn_implementation_autoset": true,
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "mel_dim": 80,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_bigvgan",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "upsample_initial_channel": 1536,
+      "upsample_kernel_sizes": [
+        11,
+        7,
+        4,
+        4,
+        4,
+        4
+      ],
+      "upsample_rates": [
+        5,
+        3,
+        2,
+        2,
+        2,
+        2
+      ],
+      "use_bfloat16": false,
+      "use_bias_at_final": false
+    },
+    "dit_config": {
+      "_attn_implementation_autoset": true,
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "block_size": 24,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "depth": 22,
+      "dim": 1024,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.1,
+      "early_stopping": false,
+      "emb_dim": 512,
+      "enc_attention_channels": 64,
+      "enc_channels": [
+        256,
+        256,
+        256,
+        256,
+        768
+      ],
+      "enc_dilations": [
+        1,
+        2,
+        3,
+        4,
+        1
+      ],
+      "enc_dim": 128,
+      "enc_emb_dim": 192,
+      "enc_global_context": true,
+      "enc_kernel_sizes": [
+        5,
+        3,
+        3,
+        3,
+        1
+      ],
+      "enc_lin_neurons": 192,
+      "enc_res2net_scale": 2,
+      "enc_se_channels": 64,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "ff_mult": 2,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 64,
+      "heads": 16,
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "look_ahead_layers": [
+        10
+      ],
+      "look_backward_layers": [
+        0,
+        20
+      ],
+      "max_length": 20,
+      "max_position_embeddings": 32768,
+      "mel_dim": 80,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_dit",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_embeds": 8193,
+      "num_hidden_layers": 22,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repeats": 2,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rope_theta": 10000.0,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": "float32",
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "model_type": "qwen2_5_omni_token2wav",
+    "torch_dtype": "float16"
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.0.dev0"
+}

openvino_token2wav_bigvgan_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e136207f00108aa77e2dfc8af408e3b7826c86dfcf3c32ec3b1078924aca233
+size 230959656

openvino_token2wav_dit_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee861e1bf6a31dc342838e819be18747a417c0d65added8b9272a31b41c190d
+size 667216186

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "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,
+  "processor_class": "Qwen2_5OmniProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|AUDIO|>",
+    "<|audio_bos|>",
+    "<|audio_eos|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_bos|>",
+    "<|vision_eos|>",
+    "<|vision_pad|>",
+    "<|IMAGE|>",
+    "<|VIDEO|>"
+  ],
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_token": "<|AUDIO|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<|IMAGE|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<|VIDEO|>",
+  "vision_bos_token": "<|vision_bos|>",
+  "vision_eos_token": "<|vision_eos|>"
+}

spk_dict.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
+size 259544

talker/openvino_talker_embedding_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd8598119993f4f77dc244e7b0c9dc65fa15f6aee29d405bd51b132fa5a2011
+size 34603012

talker/openvino_talker_embedding_model.xml

@@ -0,0 +1,107 @@
+<?xml version="1.0"?>
+<net name="Model540" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.weight" type="Const" version="opset1">
+			<data element_type="f16" shape="8448, 2048" offset="0" size="34603008" />
+			<output>
+				<port id="0" precision="FP16" names="self.weight">
+					<dim>8448</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>8448</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>8448</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="ov_ext::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="34603008" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="5" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>8448</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Result_1395264" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
+		<edge from-layer="3" from-port="1" to-layer="5" to-port="1" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="2" />
+		<edge from-layer="5" from-port="3" to-layer="6" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+	</rt_info>
+</net>

talker/openvino_talker_language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c9d314bd535bc242a5c00ff3d3c0e2297c5d0cb5b1d3fa94a982c6a946e540
+size 230992332

thinker/openvino_thinker_audio_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088e30f86b9c0bb9af6f80948c1a7a2542f0daa3406e9f1deab5c9b729819399
+size 1273932968

thinker/openvino_thinker_audio_state_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5cc6e3ab3076b77918d59d4d0c92851a07f8f7b082f58d6eb6765b66220584
+size 5252116

thinker/openvino_thinker_audio_state_model.xml

@@ -0,0 +1,372 @@
+<?xml version="1.0"?>
+<net name="Model6" version="11">
+	<layers>
+		<layer id="0" name="each_audio_states" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="each_audio_states">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_41972" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="__module.avg_pooler/aten::avg_pool1d/Unsqueeze" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="__module.avg_pooler/aten::avg_pool1d/AvgPool" type="AvgPool" version="opset14">
+			<data kernel="2" strides="2" pads_begin="0" pads_end="0" exclude-pad="false" auto_pad="explicit" rounding_type="floor" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="__module.avg_pooler/aten::avg_pool1d/Squeeze" type="Squeeze" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="21_1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="aten::transpose_/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="2" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="aten::transpose_/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.ln_post/aten::layer_norm/Multiply" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="16" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="__module.ln_post/aten::layer_norm/MVN" type="MVN" version="opset6">
+			<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="Constant_43914_compressed" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1280" offset="20" size="2560" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Constant_43914" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="__module.ln_post/aten::layer_norm/Multiply_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="Constant_43915_compressed" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1280" offset="2580" size="2560" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Constant_43915" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="__module.ln_post/aten::layer_norm/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="28">
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="self.proj.weight" type="Const" version="opset1">
+			<data element_type="f16" shape="2048, 1280" offset="5140" size="5242880" />
+			<output>
+				<port id="0" precision="FP16" names="self.proj.weight">
+					<dim>2048</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="__module.proj/ov_ext::linear/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="__module.proj/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="self.proj.bias" type="Const" version="opset1">
+			<data element_type="f16" shape="2048" offset="5248020" size="4096" />
+			<output>
+				<port id="0" precision="FP16" names="self.proj.bias">
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="__module.proj/ov_ext::linear/Convert_1" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="__module.proj/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="Result_42042" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
+		<edge from-layer="2" from-port="2" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="3" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="6" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
+		<edge from-layer="10" from-port="2" to-layer="13" to-port="0" />
+		<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
+		<edge from-layer="12" from-port="1" to-layer="13" to-port="1" />
+		<edge from-layer="13" from-port="2" to-layer="16" to-port="0" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="16" to-port="1" />
+		<edge from-layer="16" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
+		<edge from-layer="18" from-port="1" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="22" to-port="0" />
+		<edge from-layer="20" from-port="0" to-layer="21" to-port="0" />
+		<edge from-layer="21" from-port="1" to-layer="22" to-port="1" />
+		<edge from-layer="22" from-port="2" to-layer="23" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+	</rt_info>
+</net>

thinker/openvino_thinker_embedding_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9594871f4c0615216038a5c1237a975e39af3510fec22a98925d967c59ea305b
+size 622329860

thinker/openvino_thinker_embedding_model.xml

@@ -0,0 +1,107 @@
+<?xml version="1.0"?>
+<net name="Model0" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.weight" type="Const" version="opset1">
+			<data element_type="f16" shape="151936, 2048" offset="0" size="622329856" />
+			<output>
+				<port id="0" precision="FP16" names="self.weight">
+					<dim>151936</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>151936</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>151936</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="ov_ext::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="622329856" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="5" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>151936</dim>
+					<dim>2048</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Result_9" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>2048</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
+		<edge from-layer="3" from-port="1" to-layer="5" to-port="1" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="2" />
+		<edge from-layer="5" from-port="3" to-layer="6" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+	</rt_info>
+</net>

thinker/openvino_thinker_language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b77cdec2255a3a48d8e942ad4883d9c81a35d360e8b1947e673a83db48029c
+size 2022423292

thinker/openvino_thinker_merger_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edadc824e4b30b0c5c5858fc9d46b8a9914cca4c6f4c5e4a26545953df7307a1
+size 1334358176

thinker/openvino_thinker_patcher_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c86d6e62974622824e8a25fbfd2330eb2e9e182a7a524314a14e8215a2f022
+size 3010616

thinker/openvino_thinker_patcher_model.xml

@@ -0,0 +1,167 @@
+<?xml version="1.0"?>
+<net name="Model9" version="11">
+	<layers>
+		<layer id="0" name="hidden_states" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="hidden_states">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_44084" type="Const" version="opset1">
+			<data element_type="i64" shape="5" offset="0" size="40" />
+			<rt_info>
+				<attribute name="precise" version="0" />
+			</rt_info>
+			<output>
+				<port id="0" precision="I64" names="8">
+					<dim>5</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="aten::view/Reshape" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>5</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="14,9,hidden_states_1">
+					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>2</dim>
+					<dim>14</dim>
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.proj.weight_compressed" type="Const" version="opset1">
+			<data element_type="f16" shape="1280, 3, 2, 14, 14" offset="40" size="3010560" />
+			<output>
+				<port id="0" precision="FP16" names="self.proj.weight">
+					<dim>1280</dim>
+					<dim>3</dim>
+					<dim>2</dim>
+					<dim>14</dim>
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.proj.weight" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1280</dim>
+					<dim>3</dim>
+					<dim>2</dim>
+					<dim>14</dim>
+					<dim>14</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>3</dim>
+					<dim>2</dim>
+					<dim>14</dim>
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="__module.proj/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="2, 14, 14" dilations="1, 1, 1" pads_begin="0, 0, 0" pads_end="0, 0, 0" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>3</dim>
+					<dim>2</dim>
+					<dim>14</dim>
+					<dim>14</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1280</dim>
+					<dim>3</dim>
+					<dim>2</dim>
+					<dim>14</dim>
+					<dim>14</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Constant_44131" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="3010600" size="16" />
+			<rt_info>
+				<attribute name="precise" version="0" />
+			</rt_info>
+			<output>
+				<port id="0" precision="I64" names="18">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="aten::view/Reshape_1" type="Reshape" version="opset1">
+			<data special_zero="false" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="Result_44133" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1280</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
+		<edge from-layer="2" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
+		<edge from-layer="4" from-port="1" to-layer="5" to-port="1" />
+		<edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
+		<edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
+		<edge from-layer="7" from-port="2" to-layer="8" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+	</rt_info>
+</net>

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
+size 11421870

tokenizer_config.json

@@ -0,0 +1,222 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|AUDIO|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|audio_bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|audio_eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|IMAGE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|VIDEO|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|AUDIO|>",
+    "<|audio_bos|>",
+    "<|audio_eos|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_bos|>",
+    "<|vision_eos|>",
+    "<|vision_pad|>",
+    "<|IMAGE|>",
+    "<|VIDEO|>"
+  ],
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_token": "<|AUDIO|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  },
+  "image_token": "<|IMAGE|>",
+  "model_max_length": 32768,
+  "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|>"
+}