Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,181 @@
+---
+library_name: transformers
+pipeline_tag: any-to-any
+inference: true
+widget:
+  - text: Hello!
+    example_title: Hello world
+    group: Python
+---
+
+This tiny model is for debugging. It is randomly initialized with the config adapted from [Qwen/Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B).
+
+### Example usage:
+
+```python
+import soundfile as sf
+from qwen_omni_utils import process_mm_info
+from transformers import Qwen2_5OmniModel, Qwen2_5OmniProcessor
+
+model_id = "tiny-random/qwen2.5-omni"
+# model = Qwen2_5OmniModel.from_pretrained(model_id, torch_dtype="auto", device_map="auto").eval()
+# We recommend enabling flash_attention_2 for better acceleration and memory saving.
+model = Qwen2_5OmniModel.from_pretrained(
+    model_id,
+    torch_dtype="auto",
+    device_map="auto",
+    attn_implementation="flash_attention_2",
+).eval()
+processor = Qwen2_5OmniProcessor.from_pretrained(model_id)
+
+conversation = [
+    {
+        "role": "system",
+        "content": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech.",
+    },
+    {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "Hi, can you tell me a joke?"},
+            {"type": "audio", "audio": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
+            {"type": "video", "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/draw.mp4"},
+            {"type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
+        ],
+    },
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
+audios, images, videos = process_mm_info(conversation, use_audio_in_video=True)
+print('Audios:', audios)
+print('Images:', images)
+print('Videos:', videos)
+inputs = processor(text=text, audios=audios, images=images, videos=videos, return_tensors="pt", padding=True)
+inputs = inputs.to(model.device).to(model.dtype)
+
+# Inference: Generation of the output text and audio
+text_ids, audio = model.generate(
+    **inputs, use_audio_in_video=True,
+    thinker_max_new_tokens=16, talker_max_new_tokens=16,
+)
+
+text = processor.batch_decode(text_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(text, '\n' * 3)
+sf.write(
+    "/tmp/output.wav",
+    audio.reshape(-1).detach().cpu().numpy(),
+    samplerate=24000,
+)
+```
+
+### Codes to create this repo:
+
+```python
+from pathlib import Path
+
+import torch
+
+from huggingface_hub import hf_hub_download
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig,
+    Qwen2_5OmniModel,
+    Qwen2_5OmniProcessor,
+    pipeline,
+    set_seed,
+)
+
+source_model_id = "Qwen/Qwen2.5-Omni-7B"
+save_folder = "/tmp/tiny-random/qwen2.5-omni"
+
+processor = Qwen2_5OmniProcessor.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+processor.save_pretrained(save_folder)
+
+config = AutoConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+OUTPUT_DIM = 16
+config.talker_config.num_hidden_layers = 1
+config.talker_config.hidden_size = 16
+config.talker_config.embedding_size = OUTPUT_DIM
+config.talker_config.head_dim = 16
+config.talker_config.num_attention_heads = 1
+config.talker_config.num_key_value_heads = 1
+config.talker_config.intermediate_size = 32
+config.talker_config.rope_scaling['mrope_section'] = [2, 2, 4]
+assert 2 * sum(config.talker_config.rope_scaling['mrope_section']
+               ) == config.talker_config.hidden_size / config.talker_config.num_attention_heads
+
+config.thinker_config.audio_config.num_hidden_layers = 1
+config.thinker_config.audio_config.encoder_layers = 1
+config.thinker_config.audio_config.d_model = 16
+config.thinker_config.audio_config.encoder_attention_heads = 1
+config.thinker_config.audio_config.encoder_ffn_dim = 32
+config.thinker_config.audio_config.output_dim = OUTPUT_DIM
+
+config.thinker_config.text_config.num_hidden_layers = 1
+config.thinker_config.text_config.hidden_size = OUTPUT_DIM
+config.thinker_config.text_config.intermediate_size = 32
+config.thinker_config.text_config.num_attention_heads = 1
+config.thinker_config.text_config.num_key_value_heads = 1
+config.thinker_config.text_config.rope_scaling['mrope_section'] = [2, 2, 4]
+assert 2 * sum(config.thinker_config.text_config.rope_scaling['mrope_section']
+               ) == config.thinker_config.text_config.hidden_size / config.thinker_config.text_config.num_attention_heads
+
+config.thinker_config.vision_config.depth = 2
+config.thinker_config.vision_config.embed_dim = 16
+config.thinker_config.vision_config.hidden_size = 16
+config.thinker_config.vision_config.intermediate_size = 32
+config.thinker_config.vision_config.out_hidden_size = OUTPUT_DIM
+config.thinker_config.vision_config.num_heads = 1
+config.thinker_config.vision_config.fullatt_block_indexes = [1]
+
+config.token2wav_config.bigvgan_config.resblock_dilation_sizes = [[1, 3, 5]]
+config.token2wav_config.bigvgan_config.resblock_kernel_sizes = [7]
+config.token2wav_config.bigvgan_config.upsample_initial_channel = 32
+config.token2wav_config.bigvgan_config.upsample_kernel_sizes = [11, 4]
+config.token2wav_config.bigvgan_config.upsample_rates = [5, 2]
+
+config.token2wav_config.dit_config.depth = 1
+config.token2wav_config.dit_config.num_hidden_layers = 1
+config.token2wav_config.dit_config.hidden_size = 16
+config.token2wav_config.dit_config.dim = 16
+config.token2wav_config.dit_config.emb_dim = 16
+config.token2wav_config.dit_config.enc_attention_channels = 16
+config.token2wav_config.dit_config.enc_channels = [32, 32, 32]
+config.token2wav_config.dit_config.enc_dilations = [1, 3, 4]
+config.token2wav_config.dit_config.enc_kernel_sizes = [5, 3, 1]
+config.token2wav_config.dit_config.enc_dim = 16
+config.token2wav_config.dit_config.enc_emb_dim = 16
+config.token2wav_config.dit_config.enc_lin_neurons = 16
+config.token2wav_config.dit_config.head_dim = 16
+config.token2wav_config.dit_config.num_attention_heads = 1
+config.token2wav_config.dit_config.heads = 1
+# avoid mismatch in vocab size because this is random model!
+config.token2wav_config.dit_config.num_embeds = config.talker_config.vocab_size
+print(config)
+
+spk_dict = torch.load(hf_hub_download(source_model_id, 'spk_dict.pt', repo_type='model'))
+for _, info in spk_dict.items():
+    info['cond'] = info['cond'][:, :config.token2wav_config.dit_config.enc_emb_dim].clone()
+torch.save(spk_dict, Path(save_folder, "spk_dict.pt"))
+
+torch.set_default_dtype(torch.bfloat16)
+model = Qwen2_5OmniModel(
+    config,
+)
+torch.set_default_dtype(torch.float32)
+model.generation_config = GenerationConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+set_seed(42)
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.5)
+        print(name, p.shape, p.dtype)
+model.save_pretrained(save_folder)
+```

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.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,541 @@
+{
+  "architectures": [
+    "Qwen2_5OmniModel"
+  ],
+  "enable_audio_output": true,
+  "enable_talker": true,
+  "model_type": "qwen2_5_omni",
+  "talker_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "Qwen2.5-Omni-7B/talker",
+    "architectures": [
+      "Qwen2OmniTalkerForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "audio_end_token_id": 151648,
+    "audio_start_token_id": 151647,
+    "audio_token_index": 151646,
+    "embedding_size": 16,
+    "head_dim": 16,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "image_token_index": 151655,
+    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_omni_talker",
+    "num_attention_heads": 1,
+    "num_hidden_layers": 1,
+    "num_key_value_heads": 1,
+    "position_id_per_seconds": 25,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        2,
+        2,
+        4
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "seconds_per_chunk": 2,
+    "sliding_window": 32768,
+    "spatial_merge_size": 2,
+    "torch_dtype": "bfloat16",
+    "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_mrope": false,
+    "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,
+    "_name_or_path": "Qwen2.5-Omni-7B/thinker",
+    "architectures": [
+      "Qwen2OmniNaViTThinkerForConditionalGeneration"
+    ],
+    "audio_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "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": 16,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.0,
+      "early_stopping": false,
+      "encoder_attention_heads": 1,
+      "encoder_ffn_dim": 32,
+      "encoder_layerdrop": 0.0,
+      "encoder_layers": 1,
+      "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,
+      "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": 1,
+      "num_mel_bins": 128,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_dim": 16,
+      "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,
+    "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,
+      "_name_or_path": "",
+      "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": 16,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "init_std": 0.02,
+      "intermediate_size": 32,
+      "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": 28,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_text",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 1,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 1,
+      "num_key_value_heads": 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,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "mrope_section": [
+          2,
+          2,
+          4
+        ],
+        "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": true,
+      "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": 152064
+    },
+    "torch_dtype": "bfloat16",
+    "use_mrope": false,
+    "user_token_id": 872,
+    "video_token_index": 151656,
+    "vision_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "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": 2,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "embed_dim": 16,
+      "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": [
+        1
+      ],
+      "hidden_act": "silu",
+      "hidden_size": 16,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "in_chans": 3,
+      "init_std": 0.02,
+      "intermediate_size": 32,
+      "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": 1,
+      "num_return_sequences": 1,
+      "out_hidden_size": 16,
+      "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,
+      "_name_or_path": "",
+      "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
+        ]
+      ],
+      "resblock_kernel_sizes": [
+        7
+      ],
+      "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": 32,
+      "upsample_kernel_sizes": [
+        11,
+        4
+      ],
+      "upsample_rates": [
+        5,
+        2
+      ],
+      "use_bfloat16": false,
+      "use_bias_at_final": false
+    },
+    "dit_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "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": 1,
+      "dim": 16,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.1,
+      "early_stopping": false,
+      "emb_dim": 16,
+      "enc_attention_channels": 16,
+      "enc_channels": [
+        32,
+        32,
+        32
+      ],
+      "enc_dilations": [
+        1,
+        3,
+        4
+      ],
+      "enc_dim": 16,
+      "enc_emb_dim": 16,
+      "enc_global_context": true,
+      "enc_kernel_sizes": [
+        5,
+        3,
+        1
+      ],
+      "enc_lin_neurons": 16,
+      "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": 16,
+      "heads": 1,
+      "hidden_size": 16,
+      "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": 1,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_embeds": 8448,
+      "num_hidden_layers": 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,
+      "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": "bfloat16",
+  "transformers_version": "4.50.0.dev0"
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.50.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5856e6a6c48b25459916c6233cedb53ad30943caf32674d030e780e8228f022
+size 11223328

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 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spk_dict.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8294c250f1b71764778097c1785e0cb346c4365582127a851f2c5b18ae87841
+size 258136

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5OmniProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}