Qwen/Qwen2.5-Omni-7B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Qwen/Qwen2.5-Omni-7B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-06 07:54:12 +08:00
commit 8088831b05
21 changed files with 155920 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

495
config.json Normal file
View File

@@ -0,0 +1,495 @@
{
"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": 3584,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 896,
"image_token_index": 151655,
"init_std": 0.02,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2_5_omni_talker",
"num_attention_heads": 12,
"num_hidden_layers": 24,
"num_key_value_heads": 4,
"position_id_per_seconds": 25,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"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_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": 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,
"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": 3584,
"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
},
"text_config": {
"model_type": "qwen2_5_omni_text",
"hidden_act": "silu",
"hidden_size": 3584,
"init_std": 0.02,
"intermediate_size": 18944,
"vocab_size": 152064,
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"use_cache": true,
"rope_theta": 1000000.0,
"use_sliding_window": false,
"sliding_window": 32768,
"attention_dropout": 0.0,
"tie_word_embeddings": 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,
"torch_dtype": "bfloat16",
"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": 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,
"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": 3584,
"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
],
[
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,
"_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": 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,
"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_dit",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_embeds": 8193,
"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,
"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"
}