Upload 10 files

.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 %}

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 +1,248 @@
+{
+  "architectures": [
+    "Qwen2_5OmniForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "enable_audio_output": false,
+  "enable_talker": false,
+  "hidden_size": 896,
+  "intermediate_size": 2432,
+  "model_type": "qwen2_5_omni",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 2,
+  "talker_config": {},
+  "thinker_config": {
+    "_attn_implementation_autoset": true,
+    "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,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "d_model": 256,
+      "decoder_start_token_id": null,
+      "dropout": 0.0,
+      "dtype": null,
+      "encoder_attention_heads": 4,
+      "encoder_ffn_dim": 1024,
+      "encoder_layerdrop": 0.0,
+      "encoder_layers": 8,
+      "eos_token_id": null,
+      "finetuning_task": 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": "LABEL_0",
+        "LABEL_1": "LABEL_1"
+      },
+      "max_source_positions": 1500,
+      "model_type": "qwen2_5_omni_audio_encoder",
+      "n_window": 100,
+      "num_mel_bins": 128,
+      "output_attentions": false,
+      "output_dim": 896,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "return_dict": true,
+      "scale_embedding": false,
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "torchscript": false,
+      "use_bfloat16": false
+    },
+    "audio_end_token_id": 151648,
+    "audio_start_token_id": 151647,
+    "audio_token_index": 151646,
+    "bos_token_id": 151644,
+    "dtype": "bfloat16",
+    "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,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "hidden_act": "silu",
+      "hidden_size": 896,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "intermediate_size": 2432,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": "LABEL_0",
+        "LABEL_1": "LABEL_1"
+      },
+      "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+      ],
+      "max_position_embeddings": 32768,
+      "max_window_layers": 28,
+      "model_type": "qwen2_5_omni_text",
+      "mrope_section": [
+        10,
+        10,
+        20
+      ],
+      "num_attention_heads": 14,
+      "num_hidden_layers": 18,
+      "num_key_value_heads": 2,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "return_dict": true,
+      "rms_norm_eps": 1e-06,
+      "rope_parameters": {
+        "mrope_section": [
+          10,
+          10,
+          20
+        ],
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sep_token_id": null,
+      "sliding_window": null,
+      "task_specific_params": null,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "torchscript": false,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 32000
+    },
+    "tie_word_embeddings": false,
+    "user_token_id": 872,
+    "video_token_index": 151656,
+    "vision_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "depth": 12,
+      "dtype": null,
+      "embed_dim": 512,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "fullatt_block_indexes": [
+        3,
+        7,
+        11
+      ],
+      "hidden_act": "silu",
+      "hidden_size": 512,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "in_chans": 3,
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "intermediate_size": 2048,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": "LABEL_0",
+        "LABEL_1": "LABEL_1"
+      },
+      "model_type": "qwen2_5_omni_vision_encoder",
+      "num_heads": 8,
+      "out_hidden_size": 896,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "return_dict": true,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 14,
+      "task_specific_params": null,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "tokens_per_second": 25,
+      "torchscript": false,
+      "use_bfloat16": false,
+      "window_size": 16
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654
+  },
+  "token2wav_config": {},
+  "transformers_version": "5.5.4"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.5.4",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9329e687c30e9776dc066999545ab2f1fd648de9e9ee938dd53b6027c11dc1f3
+size 512376624

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:e8294c250f1b71764778097c1785e0cb346c4365582127a851f2c5b18ae87841
+size 258136

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "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,
+  "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": "<|im_end|>",
+  "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|>"
+}