Add files using upload-large-folder tool

.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
+qwen25OmniConfig/tokenizer.json filter=lfs diff=lfs merge=lfs -text

MiniOmni3_ChunkwisedEncoder.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d3e438a5a4bff83f1fa248eeec32a5b6e985b381488df771d45adc83960f9b
+size 1280756193

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

hyperparameters.yaml

@@ -0,0 +1,24 @@
+checkpoint_dir: /mnt/home/xiezhifei/projects/zh/checkpoint/stage1_paskale2e/qwen-2.5-3B
+out_dir: /data/zihang/paskal/checkpoint/train___stage_c_benchmark_v2
+devices: 8
+num_nodes: 1
+resume: false
+train:
+  save_interval: 50
+  log_interval: 3
+  global_batch_size: 64
+  micro_batch_size: 2
+  lr_warmup_steps: 100
+  epochs: 2
+  max_seq_length: 4096
+  min_lr: 6.0e-05
+eval:
+  interval: 25
+  max_new_tokens: 2000
+  max_iters: 500
+  initial_validation: true
+  final_validation: true
+  evaluate_example: first
+optimizer: AdamW
+logger_name: tensorboard
+seed: 1337

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10515031694eab7c284f43a6866b2fc569ab2fca2bfc84afad07a19cb91b6f2b
+size 3940686120

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2225da7d4313ea645ddd27b88d95e177af894feda93ede872c826a23e9e93122
+size 3917837088

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78d5bd16d98b24295b5e986ec45c9ec4811309a68e20dcafc8a8866cabe3a17
+size 3917837144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a7f57635a6f9c209cf75752d15897540cc3cadba32aed283e614112d4e9a65
+size 1812085376

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13588414464
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "transformer.wte.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.norm_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.norm_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.fc_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.fc_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.norm_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.norm_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.fc_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.fc_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.norm_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.norm_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.fc_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.fc_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.norm_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.norm_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.fc_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.fc_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.norm_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.norm_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.fc_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.fc_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.5.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.5.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.6.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.6.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.7.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.7.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.8.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.8.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.9.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.9.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.10.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.10.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.11.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.11.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.12.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.fc_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.norm_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.norm_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.mlp.fc_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.17.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.18.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.18.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.19.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.19.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.20.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.20.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.21.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.21.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.22.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.22.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.23.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.23.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.24.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.24.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.25.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.fc_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.fc_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.norm_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.norm_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.mlp.fc_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.30.mlp.fc_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.30.mlp.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.norm_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.31.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.norm_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.mlp.fc_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.mlp.fc_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.31.mlp.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.norm_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.32.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.norm_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.mlp.fc_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.mlp.fc_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.32.mlp.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.norm_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.33.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.norm_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.mlp.fc_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.mlp.fc_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.33.mlp.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.norm_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.34.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.norm_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.mlp.fc_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.mlp.fc_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.34.mlp.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.norm_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.35.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.norm_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.mlp.fc_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.mlp.fc_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.35.mlp.proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.ln_f.weight": "model-00004-of-00004.safetensors"
+  }
+}

model_config.yaml

@@ -0,0 +1,38 @@
+attention_logit_softcapping: null
+attention_scores_scalar: null
+attn_bias: true
+bias: false
+block_size: 32768
+final_logit_softcapping: null
+gelu_approximate: none
+head_size: 128
+hf_config:
+  name: Qwen2.5-3B
+  org: Qwen
+intermediate_size: 11008
+lm_head_bias: false
+mlp_class_name: LLaMAMLP
+n_embd: 2048
+n_expert: 0
+n_expert_per_token: 0
+n_head: 16
+n_layer: 36
+n_query_groups: 2
+name: Qwen2.5-3B
+norm_class_name: RMSNorm
+norm_eps: 1.0e-06
+norm_qk: false
+padded_vocab_size: 151936
+padding_multiple: 512
+parallel_residual: false
+post_attention_norm: false
+post_mlp_norm: false
+rope_adjustments: null
+rope_base: 1000000
+rope_condense_ratio: 1
+rotary_percentage: 1.0
+scale_embeddings: false
+shared_attention_norm: false
+sliding_window_layer_placing: null
+sliding_window_size: null
+vocab_size: 151643

qwen25OmniConfig/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

qwen25OmniConfig/LICENSE

@@ -0,0 +1,53 @@
+Qwen RESEARCH LICENSE AGREEMENT
+
+Qwen RESEARCH LICENSE AGREEMENT Release Date: September 19, 2024
+
+By clicking to agree or by using or distributing any portion or element of the Qwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
+
+1. Definitions
+    a. This Qwen RESEARCH LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
+    b. "We" (or "Us") shall mean Alibaba Cloud.
+    c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
+    d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
+    e. "Qwen" shall mean the large language models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by us.
+    f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Qwen and Documentation (and any portion thereof) made available under this Agreement.
+    g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
+    h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+    i. "Non-Commercial" shall mean for research or evaluation purposes only.
+
+2. Grant of Rights
+    a. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's intellectual property or other rights owned by us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials FOR NON-COMMERCIAL PURPOSES ONLY. 
+    b. If you are commercially using the Materials, you shall request a license from us.
+
+3. Redistribution
+You may distribute copies or make the Materials, or derivative works thereof, available as part of a product or service that contains any of them, with or without modifications, and in Source or Object form, provided that you meet the following conditions:
+    a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
+    b. You shall cause any modified files to carry prominent notices stating that you changed the files;
+    c. You shall retain in all copies of the Materials that you distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
+    d. You may add your own copyright statement to your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of your modifications, or for any such derivative works as a whole, provided your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
+
+4. Rules of use
+    a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
+    b. If you use the Materials or any outputs or results therefrom to create, train, fine-tune, or improve an AI model that is distributed or made available, you shall prominently display “Built with Qwen” or “Improved using Qwen” in the related product documentation.
+
+5. Intellectual Property
+    a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
+    b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
+    c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licenses granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
+6. Disclaimer of Warranty and Limitation of Liability
+    a. We are not obligated to support, update, provide training for, or develop any further version of the Qwen Materials or to grant any license thereto.
+    b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
+    c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
+    d. You will defend, indemnify and hold harmless us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
+
+7. Survival and Termination.
+    a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
+    b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 6 and 8 shall survive the termination of this Agreement.
+
+8. Governing Law and Jurisdiction.
+    a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+    b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
+9. Other Terms and Conditions.
+    a. Any arrangements, understandings, or agreements regarding the Material not stated herein are separate from and independent of the terms and conditions of this Agreement. You shall request a separate license from us, if you use the Materials in ways not expressly agreed to in this Agreement. 
+    b. We shall not be bound by any additional or different terms or conditions communicated by you unless expressly agreed.
+

qwen25OmniConfig/README.md

@@ -0,0 +1,983 @@
+---
+license: other
+license_name: qwen-research
+license_link: LICENSE
+language:
+- en
+tags:
+- multimodal
+library_name: transformers
+pipeline_tag: any-to-any
+---
+
+# Qwen2.5-Omni
+<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+
+## Overview 
+### Introduction
+Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. 
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/qwen_omni.png" width="80%"/>
+<p>
+
+### Key Features
+
+* **Omni and Novel Architecture**: We propose Thinker-Talker architecture, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. We propose a novel position embedding, named TMRoPE (Time-aligned Multimodal RoPE), to synchronize the timestamps of video inputs with audio.
+
+* **Real-Time Voice and Video Chat**: Architecture designed for fully real-time interactions, supporting chunked input and immediate output.
+
+* **Natural and Robust Speech Generation**: Surpassing many existing streaming and non-streaming alternatives, demonstrating superior robustness and naturalness in speech generation.
+
+* **Strong Performance Across Modalities**: Exhibiting exceptional performance across all modalities when benchmarked against similarly sized single-modality models. Qwen2.5-Omni outperforms the similarly sized Qwen2-Audio in audio capabilities and achieves comparable performance to Qwen2.5-VL-7B.
+
+* **Excellent End-to-End Speech Instruction Following**: Qwen2.5-Omni shows performance in end-to-end speech instruction following that rivals its effectiveness with text inputs, evidenced by benchmarks such as MMLU and GSM8K.
+
+### Model Architecture
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/overview.png" width="80%"/>
+<p>
+
+### Performance
+
+We conducted a comprehensive evaluation of Qwen2.5-Omni, which demonstrates strong performance across all modalities when compared to similarly sized single-modality models and closed-source models like Qwen2.5-VL-7B, Qwen2-Audio, and Gemini-1.5-pro. In tasks requiring the integration of multiple modalities, such as OmniBench, Qwen2.5-Omni achieves state-of-the-art performance. Furthermore, in single-modality tasks, it excels in areas including speech recognition (Common Voice), translation (CoVoST2), audio understanding (MMAU), image reasoning (MMMU, MMStar), video understanding (MVBench), and speech generation (Seed-tts-eval and subjective naturalness).
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/bar.png" width="80%"/>
+<p>
+
+<details>
+<summary>Multimodality  -> Text</summary>
+
+<table class="tg"><thead>
+  <tr>
+    <th class="tg-0lax">Datasets</th>
+    <th class="tg-0lax">Model</th>
+    <th class="tg-0lax">Performance</th>
+  </tr></thead>
+<tbody>
+  <tr>
+    <td class="tg-0lax" rowspan="10">OmniBench<br>Speech | Sound Event | Music | Avg</td>
+    <td class="tg-0lax">Gemini-1.5-Pro</td>
+    <td class="tg-0lax">42.67%|42.26%|46.23%|42.91%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MIO-Instruct</td>
+    <td class="tg-0lax">36.96%|33.58%|11.32%|33.80%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">AnyGPT (7B)</td>
+    <td class="tg-0lax">17.77%|20.75%|13.21%|18.04%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">video-SALMONN</td>
+    <td class="tg-0lax">34.11%|31.70%|<strong>56.60%</strong>|35.64%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">UnifiedIO2-xlarge</td>
+    <td class="tg-0lax">39.56%|36.98%|29.25%|38.00%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">UnifiedIO2-xxlarge</td>
+    <td class="tg-0lax">34.24%|36.98%|24.53%|33.98%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">-|-|-|40.50%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Baichuan-Omni-1.5</td>
+    <td class="tg-0lax">-|-|-|42.90%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">52.14%|52.08%|52.83%|52.19%</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>55.25%</strong>|<strong>60.00%</strong>|52.83%|<strong>56.13%</strong></td>
+  </tr>
+</tbody></table>
+</details>
+
+
+<details>
+<summary>Audio -> Text</summary>
+
+
+<table class="tg"><thead>
+  <tr>
+    <th class="tg-0lax">Datasets</th>
+    <th class="tg-0lax">Model</th>
+    <th class="tg-0lax">Performance</th>
+  </tr></thead>
+<tbody>
+  <tr>
+    <td class="tg-9j4x" colspan="3">ASR</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="12">Librispeech<br>dev-clean | dev other | test-clean | test-other</td>
+    <td class="tg-0lax">SALMONN</td>
+    <td class="tg-0lax">-|-|2.1|4.9</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">SpeechVerse</td>
+    <td class="tg-0lax">-|-|2.1|4.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Whisper-large-v3</td>
+    <td class="tg-0lax">-|-|1.8|3.6</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Llama-3-8B</td>
+    <td class="tg-0lax">-|-|-|3.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Llama-3-70B</td>
+    <td class="tg-0lax">-|-|-|3.1</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Seed-ASR-Multilingual</td>
+    <td class="tg-0lax">-|-|<strong>1.6</strong>|<strong>2.8</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">-|-|1.7|-</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MinMo</td>
+    <td class="tg-0lax">-|-|1.7|3.9</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen-Audio</td>
+    <td class="tg-0lax">1.8|4.0|2.0|4.2</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax"><strong>1.3</strong>|<strong>3.4</strong>|<strong>1.6</strong>|3.6</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">2.0|4.1|2.2|4.5</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax">1.6|3.5|1.8|3.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="5">Common Voice 15<br>en | zh | yue | fr</td>
+    <td class="tg-0lax">Whisper-large-v3</td>
+    <td class="tg-0lax">9.3|12.8|10.9|10.8</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MinMo</td>
+    <td class="tg-0lax">7.9|6.3|6.4|8.5</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">8.6|6.9|<strong>5.9</strong>|9.6</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">9.1|6.0|11.6|9.6</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>7.6</strong>|<strong>5.2</strong>|7.3|<strong>7.5</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="8">Fleurs<br>zh | en</td>
+    <td class="tg-0lax">Whisper-large-v3</td>
+    <td class="tg-0lax">7.7|4.1</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Seed-ASR-Multilingual</td>
+    <td class="tg-0lax">-|<strong>3.4</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Megrez-3B-Omni</td>
+    <td class="tg-0lax">10.8|-</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">4.4|-</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MinMo</td>
+    <td class="tg-0lax">3.0|3.8</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">7.5|-</td>
+  </tr>
+    <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">3.2|5.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>3.0</strong>|4.1</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="6">Wenetspeech<br>test-net | test-meeting</td>
+    <td class="tg-0lax">Seed-ASR-Chinese</td>
+    <td class="tg-0lax"><strong>4.7|5.7</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Megrez-3B-Omni</td>
+    <td class="tg-0lax">-|16.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">6.9|-</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MinMo</td>
+    <td class="tg-0lax">6.8|7.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">6.3|8.1</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax">5.9|7.7</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="4">Voxpopuli-V1.0-en</td>
+    <td class="tg-0lax">Llama-3-8B</td>
+    <td class="tg-0lax">6.2</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Llama-3-70B</td>
+    <td class="tg-0lax"><strong>5.7</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">6.6</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax">5.8</td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">S2TT</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="9">CoVoST2<br>en-de | de-en | en-zh | zh-en</td>
+    <td class="tg-0lax">SALMONN</td>
+    <td class="tg-0lax">18.6|-|33.1|-</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">SpeechLLaMA</td>
+    <td class="tg-0lax">-|27.1|-|12.3</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">BLSP</td>
+    <td class="tg-0lax">14.1|-|-|-</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">-|-|<strong>48.2</strong>|27.2</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MinMo</td>
+    <td class="tg-0lax">-|<strong>39.9</strong>|46.7|26.0</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen-Audio</td>
+    <td class="tg-0lax">25.1|33.9|41.5|15.7</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">29.9|35.2|45.2|24.4</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">28.3|38.1|41.4|26.6</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>30.2</strong>|37.7|41.4|<strong>29.4</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">SER</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="6">Meld</td>
+    <td class="tg-0lax">WavLM-large</td>
+    <td class="tg-0lax">0.542</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">0.524</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen-Audio</td>
+    <td class="tg-0lax">0.557</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">0.553</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">0.558</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>0.570</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">VSC</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="6">VocalSound</td>
+    <td class="tg-0lax">CLAP</td>
+    <td class="tg-0lax">0.495</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Pengi</td>
+    <td class="tg-0lax">0.604</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen-Audio</td>
+    <td class="tg-0lax">0.929</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax"><strong>0.939</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">0.936</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>0.939</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">Music</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="3">GiantSteps Tempo</td>
+    <td class="tg-0lax">Llark-7B</td>
+    <td class="tg-0lax">0.86</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax"><strong>0.88</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>0.88</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="3">MusicCaps</td>
+    <td class="tg-0lax">LP-MusicCaps</td>
+    <td class="tg-0lax">0.291|0.149|0.089|<strong>0.061</strong>|0.129|0.130</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">0.325|<strong>0.163</strong>|<strong>0.093</strong>|0.057|<strong>0.132</strong>|<strong>0.229</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>0.328</strong>|0.162|0.090|0.055|0.127|0.225</td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">Audio Reasoning</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="4">MMAU<br>Sound | Music | Speech | Avg</td>
+    <td class="tg-0lax">Gemini-Pro-V1.5</td>
+    <td class="tg-0lax">56.75|49.40|58.55|54.90</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">54.95|50.98|42.04|49.20</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax"><strong>70.27</strong>|60.48|59.16|63.30</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax">67.87|<strong>69.16|59.76|65.60</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">Voice Chatting</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="9">VoiceBench<br>AlpacaEval | CommonEval | SD-QA | MMSU</td>
+    <td class="tg-0lax">Ultravox-v0.4.1-LLaMA-3.1-8B</td>
+    <td class="tg-0lax"><strong>4.55</strong>|3.90|53.35|47.17</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MERaLiON</td>
+    <td class="tg-0lax">4.50|3.77|55.06|34.95</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Megrez-3B-Omni</td>
+    <td class="tg-0lax">3.50|2.95|25.95|27.03</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Lyra-Base</td>
+    <td class="tg-0lax">3.85|3.50|38.25|49.74</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">4.42|<strong>4.15</strong>|50.72|54.78</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Baichuan-Omni-1.5</td>
+    <td class="tg-0lax">4.50|4.05|43.40|57.25</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">3.74|3.43|35.71|35.72</td>
+  </tr>
+    <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">4.32|4.00|49.37|50.23</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax">4.49|3.93|<strong>55.71</strong>|<strong>61.32</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="9">VoiceBench<br>OpenBookQA | IFEval | AdvBench | Avg</td>
+    <td class="tg-0lax">Ultravox-v0.4.1-LLaMA-3.1-8B</td>
+    <td class="tg-0lax">65.27|<strong>66.88</strong>|98.46|71.45</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MERaLiON</td>
+    <td class="tg-0lax">27.23|62.93|94.81|62.91</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Megrez-3B-Omni</td>
+    <td class="tg-0lax">28.35|25.71|87.69|46.25</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Lyra-Base</td>
+    <td class="tg-0lax">72.75|36.28|59.62|57.66</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MiniCPM-o</td>
+    <td class="tg-0lax">78.02|49.25|97.69|71.69</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Baichuan-Omni-1.5</td>
+    <td class="tg-0lax">74.51|54.54|97.31|71.14</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2-Audio</td>
+    <td class="tg-0lax">49.45|26.33|96.73|55.35</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B</td>
+    <td class="tg-0lax">74.73|42.10|98.85|68.81</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B</td>
+    <td class="tg-0lax"><strong>81.10</strong>|52.87|<strong>99.42</strong>|<strong>74.12</strong></td>
+  </tr>
+</tbody></table>
+</details>
+
+<details>
+<summary>Image -> Text</summary>
+
+| Dataset                        | Qwen2.5-Omni-7B | Qwen2.5-Omni-3B | Other Best | Qwen2.5-VL-7B | GPT-4o-mini | 
+|--------------------------------|--------------|------------|------------|---------------|-------------|
+| MMMU<sub>val</sub>             | 59.2         | 53.1       | 53.9       | 58.6          | **60.0**    | 
+| MMMU-Pro<sub>overall</sub>     | 36.6         | 29.7       | -          | **38.3**      | 37.6        | 
+| MathVista<sub>testmini</sub>   | 67.9         | 59.4       | **71.9**   | 68.2          | 52.5        | 
+| MathVision<sub>full</sub>      | 25.0         | 20.8       | 23.1       | **25.1**      | -           | 
+| MMBench-V1.1-EN<sub>test</sub> | 81.8         | 77.8       | 80.5       | **82.6**      | 76.0        | 
+| MMVet<sub>turbo</sub>          | 66.8         | 62.1       | **67.5**   | 67.1          | 66.9        | 
+| MMStar                         | **64.0**     | 55.7       | **64.0**   | 63.9          | 54.8        | 
+| MME<sub>sum</sub>              | 2340         | 2117       | **2372**   | 2347          | 2003        | 
+| MuirBench                      | 59.2         | 48.0       | -          | **59.2**      | -           | 
+| CRPE<sub>relation</sub>        | **76.5**     | 73.7       | -          | 76.4          | -           | 
+| RealWorldQA<sub>avg</sub>      | 70.3         | 62.6       | **71.9**   | 68.5          | -           | 
+| MME-RealWorld<sub>en</sub>     | **61.6**     | 55.6       | -          | 57.4          | -           | 
+| MM-MT-Bench                    | 6.0          | 5.0        | -          | **6.3**       | -           | 
+| AI2D                           | 83.2         | 79.5       | **85.8**   | 83.9          | -           | 
+| TextVQA<sub>val</sub>          | 84.4         | 79.8       | 83.2       | **84.9**      | -           | 
+| DocVQA<sub>test</sub>          | 95.2         | 93.3       | 93.5       | **95.7**      | -           | 
+| ChartQA<sub>test Avg</sub>     | 85.3         | 82.8       | 84.9       | **87.3**      | -           | 
+| OCRBench_V2<sub>en</sub>       | **57.8**     | 51.7       | -          | 56.3          | -           | 
+
+
+| Dataset                  | Qwen2.5-Omni-7B | Qwen2.5-Omni-3B | Qwen2.5-VL-7B | Grounding DINO | Gemini 1.5 Pro | 
+|--------------------------|--------------|---------------|---------------|----------------|----------------|
+| Refcoco<sub>val</sub>    | 90.5         | 88.7          | 90.0          | **90.6**       | 73.2           | 
+| Refcoco<sub>textA</sub>  | **93.5**     | 91.8          | 92.5          | 93.2           | 72.9           | 
+| Refcoco<sub>textB</sub>  | 86.6         | 84.0          | 85.4          | **88.2**       | 74.6           | 
+| Refcoco+<sub>val</sub>   | 85.4         | 81.1          | 84.2          | **88.2**       | 62.5           | 
+| Refcoco+<sub>textA</sub> | **91.0**     | 87.5          | 89.1          | 89.0           | 63.9           | 
+| Refcoco+<sub>textB</sub> | **79.3**     | 73.2          | 76.9          | 75.9           | 65.0           | 
+| Refcocog+<sub>val</sub>  | **87.4**     | 85.0          | 87.2          | 86.1           | 75.2           | 
+| Refcocog+<sub>test</sub> | **87.9**     | 85.1          | 87.2          | 87.0           | 76.2           | 
+| ODinW                    | 42.4         | 39.2          | 37.3          | **55.0**       | 36.7           | 
+| PointGrounding           | 66.5         | 46.2          | **67.3**      | -              | -              | 
+</details>
+
+
+<details>
+<summary>Video(without audio) -> Text</summary>
+
+| Dataset                     | Qwen2.5-Omni-7B | Qwen2.5-Omni-3B | Other Best | Qwen2.5-VL-7B | GPT-4o-mini | 
+|-----------------------------|--------------|------------|------------|---------------|-------------|
+| Video-MME<sub>w/o sub</sub> | 64.3         | 62.0       | 63.9       | **65.1**      | 64.8        | 
+| Video-MME<sub>w sub</sub>   | **72.4**     | 68.6       | 67.9       | 71.6          | -           | 
+| MVBench                     | **70.3**     | 68.7       | 67.2       | 69.6          | -           | 
+| EgoSchema<sub>test</sub>    | **68.6**     | 61.4       | 63.2       | 65.0          | -           | 
+</details>
+
+<details>
+<summary>Zero-shot Speech Generation</summary>
+
+
+<table class="tg"><thead>
+  <tr>
+    <th class="tg-0lax">Datasets</th>
+    <th class="tg-0lax">Model</th>
+    <th class="tg-0lax">Performance</th>
+  </tr></thead>
+<tbody>
+  <tr>
+    <td class="tg-9j4x" colspan="3">Content Consistency</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="11">SEED<br>test-zh | test-en | test-hard </td>
+    <td class="tg-0lax">Seed-TTS_ICL</td>
+    <td class="tg-0lax">1.11 | 2.24 | 7.58</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Seed-TTS_RL</td>
+    <td class="tg-0lax"><strong>1.00</strong> | 1.94 | <strong>6.42</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MaskGCT</td>
+    <td class="tg-0lax">2.27 | 2.62 | 10.27</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">E2_TTS</td>
+    <td class="tg-0lax">1.97 | 2.19 | -</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">F5-TTS</td>
+    <td class="tg-0lax">1.56 | <strong>1.83</strong> | 8.67</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">CosyVoice 2</td>
+    <td class="tg-0lax">1.45 | 2.57 | 6.83</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">CosyVoice 2-S</td>
+    <td class="tg-0lax">1.45 | 2.38 | 8.08</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B_ICL</td>
+    <td class="tg-0lax">1.95 | 2.87 | 9.92</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B_RL</td>
+    <td class="tg-0lax">1.58 | 2.51 | 7.86</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B_ICL</td>
+    <td class="tg-0lax">1.70 | 2.72 | 7.97</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B_RL</td>
+    <td class="tg-0lax">1.42 | 2.32 | 6.54</td>
+  </tr>
+  <tr>
+    <td class="tg-9j4x" colspan="3">Speaker Similarity</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax" rowspan="11">SEED<br>test-zh | test-en | test-hard </td>
+    <td class="tg-0lax">Seed-TTS_ICL</td>
+    <td class="tg-0lax">0.796 | 0.762 | 0.776</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Seed-TTS_RL</td>
+    <td class="tg-0lax"><strong>0.801</strong> | <strong>0.766</strong> | <strong>0.782</strong></td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">MaskGCT</td>
+    <td class="tg-0lax">0.774 | 0.714 | 0.748</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">E2_TTS</td>
+    <td class="tg-0lax">0.730 | 0.710 | -</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">F5-TTS</td>
+    <td class="tg-0lax">0.741 | 0.647 | 0.713</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">CosyVoice 2</td>
+    <td class="tg-0lax">0.748 | 0.652 | 0.724</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">CosyVoice 2-S</td>
+    <td class="tg-0lax">0.753 | 0.654 | 0.732</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B_ICL</td>
+    <td class="tg-0lax">0.741 | 0.635 | 0.748</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-3B_RL</td>
+    <td class="tg-0lax">0.744 | 0.635 | 0.746</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B_ICL</td>
+    <td class="tg-0lax">0.752 | 0.632 | 0.747</td>
+  </tr>
+  <tr>
+    <td class="tg-0lax">Qwen2.5-Omni-7B_RL</td>
+    <td class="tg-0lax">0.754 | 0.641 | 0.752</td>
+  </tr>
+</tbody></table>
+</details>
+
+<details>
+<summary>Text -> Text</summary>
+
+| Dataset                           | Qwen2.5-Omni-7B | Qwen2.5-Omni-3B | Qwen2.5-7B | Qwen2.5-3B | Qwen2-7B | Llama3.1-8B | Gemma2-9B | 
+|-----------------------------------|-----------|------------|------------|------------|------------|-------------|-----------|
+| MMLU-Pro                          | 47.0      | 40.4       | **56.3**   | 43.7       | 44.1       | 48.3        | 52.1      | 
+| MMLU-redux                        | 71.0      | 60.9       | **75.4**   | 64.4       | 67.3       | 67.2        | 72.8      | 
+| LiveBench<sub>0831</sub>          | 29.6      | 22.3       | **35.9**   | 26.8       | 29.2       | 26.7        | 30.6      | 
+| GPQA                              | 30.8      | 34.3       | **36.4**   | 30.3       | 34.3       | 32.8        | 32.8      | 
+| MATH                              | 71.5      | 63.6       | **75.5**   | 65.9       | 52.9       | 51.9        | 44.3      | 
+| GSM8K                             | 88.7      | 82.6       | **91.6**   | 86.7       | 85.7       | 84.5        | 76.7      | 
+| HumanEval                         | 78.7      | 70.7       | **84.8**   |	74.4       | 79.9       | 72.6        | 68.9      | 
+| MBPP                              | 73.2      | 70.4       | **79.2**   | 72.7       | 67.2       | 69.6        | 74.9      | 
+| MultiPL-E                         | 65.8      | 57.6       | **70.4**   | 60.2       | 59.1       | 50.7        | 53.4      | 
+| LiveCodeBench<sub>2305-2409</sub> | 24.6      | 16.5       | **28.7**   | 19.9       | 23.9       | 8.3         | 18.9      | 
+</details>
+
+## Quickstart
+
+Below, we provide simple examples to show how to use Qwen2.5-Omni with 🤗 Transformers. The codes of Qwen2.5-Omni has been in the latest Hugging face transformers and we advise you to build from source with command:
+```
+pip uninstall transformers
+pip install git+https://github.com/huggingface/transformers@v4.51.3-Qwen2.5-Omni-preview
+pip install accelerate
+```
+or you might encounter the following error:
+```
+KeyError: 'qwen2_5_omni'
+```
+
+
+We offer a toolkit to help you handle various types of audio and visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved audio, images and videos. You can install it using the following command and make sure your system has `ffmpeg` installed:
+
+```bash
+# It's highly recommended to use `[decord]` feature for faster video loading.
+pip install qwen-omni-utils[decord] -U
+```
+
+If you are not using Linux, you might not be able to install `decord` from PyPI. In that case, you can use `pip install qwen-omni-utils -U` which will fall back to using torchvision for video processing. However, you can still [install decord from source](https://github.com/dmlc/decord?tab=readme-ov-file#install-from-source) to get decord used when loading video.
+
+### 🤗  Transformers Usage
+
+Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_omni_utils`:
+
+```python
+import soundfile as sf
+
+from transformers import Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniProcessor
+from qwen_omni_utils import process_mm_info
+
+# default: Load the model on the available device(s)
+model = Qwen2_5OmniForConditionalGeneration.from_pretrained("Qwen/Qwen2.5-Omni-3B", torch_dtype="auto", device_map="auto")
+
+# We recommend enabling flash_attention_2 for better acceleration and memory saving.
+# model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
+#     "Qwen/Qwen2.5-Omni-3B",
+#     torch_dtype="auto",
+#     device_map="auto",
+#     attn_implementation="flash_attention_2",
+# )
+
+processor = Qwen2_5OmniProcessor.from_pretrained("Qwen/Qwen2.5-Omni-3B")
+
+conversation = [
+    {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "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": "video", "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/draw.mp4"},
+        ],
+    },
+]
+
+# set use audio in video
+USE_AUDIO_IN_VIDEO = True
+
+# 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=USE_AUDIO_IN_VIDEO)
+inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
+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=USE_AUDIO_IN_VIDEO)
+
+text = processor.batch_decode(text_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(text)
+sf.write(
+    "output.wav",
+    audio.reshape(-1).detach().cpu().numpy(),
+    samplerate=24000,
+)
+```
+
+<details>
+<summary>Minimum GPU memory requirements</summary>
+
+|Model | Precision | 15(s) Video | 30(s) Video | 60(s) Video |
+|--------------|-----------| ------------- | ------------- | ------------------ |
+| Qwen-Omni-3B | FP32      | 89.10 GB      | Not Recommend | Not Recommend      |
+| Qwen-Omni-3B | BF16      | 18.38 GB      | 22.43 GB      | 28.22 GB           |
+| Qwen-Omni-7B | FP32      | 93.56 GB      | Not Recommend | Not Recommend      |
+| Qwen-Omni-7B | BF16      | 31.11 GB      | 41.85 GB      | 60.19 GB           |
+
+Note: The table above presents the theoretical minimum memory requirements for inference with `transformers` and `BF16` is test with `attn_implementation="flash_attention_2"`; however, in practice, the actual memory usage is typically at least 1.2 times higher. For more information, see the linked resource [here](https://huggingface.co/docs/accelerate/main/en/usage_guides/model_size_estimator).
+</details>  
+
+<details>
+<summary>Video URL resource usage</summary>
+
+Video URL compatibility largely depends on the third-party library version. The details are in the table below. Change the backend by `FORCE_QWENVL_VIDEO_READER=torchvision` or `FORCE_QWENVL_VIDEO_READER=decord` if you prefer not to use the default one.
+
+| Backend     | HTTP | HTTPS |
+|-------------|------|-------|
+| torchvision >= 0.19.0 | ✅  | ✅   |
+| torchvision < 0.19.0  | ❌  | ❌   |
+| decord      | ✅  | ❌   |
+</details>
+
+<details>
+<summary>Batch inference</summary>
+
+The model can batch inputs composed of mixed samples of various types such as text, images, audio and videos as input when `return_audio=False` is set. Here is an example.
+
+```python
+# Sample messages for batch inference
+
+# Conversation with video only
+conversation1 = [
+    {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "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": "video", "video": "/path/to/video.mp4"},
+        ]
+    }
+]
+
+# Conversation with audio only
+conversation2 = [
+    {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "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": "audio", "audio": "/path/to/audio.wav"},
+        ]
+    }
+]
+
+# Conversation with pure text
+conversation3 = [
+    {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "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": "who are you?"
+    }
+]
+
+
+# Conversation with mixed media
+conversation4 = [
+    {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "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": "image", "image": "/path/to/image.jpg"},
+            {"type": "video", "video": "/path/to/video.mp4"},
+            {"type": "audio", "audio": "/path/to/audio.wav"},
+            {"type": "text", "text": "What are the elements can you see and hear in these medias?"},
+        ],
+    }
+]
+
+# Combine messages for batch processing
+conversations = [conversation1, conversation2, conversation3, conversation4]
+
+# set use audio in video
+USE_AUDIO_IN_VIDEO = True
+
+# Preparation for batch inference
+text = processor.apply_chat_template(conversations, add_generation_prompt=True, tokenize=False)
+audios, images, videos = process_mm_info(conversations, use_audio_in_video=USE_AUDIO_IN_VIDEO)
+
+inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
+inputs = inputs.to(model.device).to(model.dtype)
+
+# Batch Inference
+text_ids = model.generate(**inputs, use_audio_in_video=USE_AUDIO_IN_VIDEO, return_audio=False)
+text = processor.batch_decode(text_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(text)
+```
+</details>
+
+### Usage Tips
+
+#### Prompt for audio output
+If users need audio output, the system prompt must be set as "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.", otherwise the audio output may not work as expected.
+```
+{
+    "role": "system",
+    "content": [
+        {"type": "text", "text": "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."}
+    ],
+}
+```
+#### Use audio in video
+In the process of multimodal interaction, the videos provided by users are often accompanied by audio (such as questions about the content in the video, or sounds generated by certain events in the video). This information is conducive to the model providing a better interactive experience. So we provide the following options for users to decide whether to use audio in video.
+```python
+# first place, in data preprocessing
+audios, images, videos = process_mm_info(conversations, use_audio_in_video=True)
+```
+```python
+# second place, in model processor
+inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", 
+                   padding=True, use_audio_in_video=True)
+```
+```python
+#  third place, in model inference
+text_ids, audio = model.generate(**inputs, use_audio_in_video=True)
+```
+It is worth noting that during a multi-round conversation, the `use_audio_in_video` parameter in these places must be set to the same, otherwise unexpected results will occur.
+
+#### Use audio output or not
+
+The model supports both text and audio outputs, if users do not need audio outputs, they can call `model.disable_talker()` after init the model. This option will save about `~2GB` of GPU memory but the `return_audio` option for `generate` function will only allow to be set at `False`.
+```python
+model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2.5-Omni-3B",
+    torch_dtype="auto",
+    device_map="auto"
+)
+model.disable_talker()
+```
+
+In order to obtain a flexible experience, we recommend that users can decide whether to return audio when `generate` function is called. If `return_audio` is set to `False`, the model will only return text outputs to get text responses faster.
+
+```python
+model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2.5-Omni-3B",
+    torch_dtype="auto",
+    device_map="auto"
+)
+...
+text_ids = model.generate(**inputs, return_audio=False)
+```
+
+#### Change voice type of output audio
+Qwen2.5-Omni supports the ability to change the voice of the output audio. The `"Qwen/Qwen2.5-Omni-3B"` checkpoint support two voice types as follow:
+
+| Voice Type | Gender | Description |
+|------------|--------|-------------|
+| Chelsie    | Female | A honeyed, velvety voice that carries a gentle warmth and luminous clarity.|
+| Ethan      | Male   | A bright, upbeat voice with infectious energy and a warm, approachable vibe.|
+
+Users can use the `speaker` parameter of `generate` function to specify the voice type. By default, if `speaker` is not specified, the default voice type is `Chelsie`.
+
+```python
+text_ids, audio = model.generate(**inputs, speaker="Chelsie")
+```
+
+```python
+text_ids, audio = model.generate(**inputs, speaker="Ethan")
+```
+
+#### Flash-Attention 2 to speed up generation
+
+First, make sure to install the latest version of Flash Attention 2:
+
+```bash
+pip install -U flash-attn --no-build-isolation
+```
+
+Also, you should have hardware that is compatible with FlashAttention 2. Read more about it in the official documentation of the [flash attention repository](https://github.com/Dao-AILab/flash-attention). FlashAttention-2 can only be used when a model is loaded in `torch.float16` or `torch.bfloat16`.
+
+To load and run a model using FlashAttention-2, add `attn_implementation="flash_attention_2"` when loading the model:
+
+```python
+from transformers import Qwen2_5OmniForConditionalGeneration
+
+model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2.5-Omni-3B",
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+)
+```
+
+
+## Citation
+
+If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
+
+
+
+```BibTeX
+
+@article{Qwen2.5-Omni,
+  title={Qwen2.5-Omni Technical Report},
+  author={Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, Bin Zhang, Xiong Wang, Yunfei Chu, Junyang Lin},
+  journal={arXiv preprint arXiv:2503.20215},
+  year={2025}
+}
+```
+
+<br>
+

qwen25OmniConfig/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
+}

qwen25OmniConfig/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 %}"
+}

qwen25OmniConfig/config.json

@@ -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-3B/talker",
+    "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": "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-3B/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": 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
+    },
+    "text_config": {
+      "model_type": "qwen2_5_omni_text",
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "init_std": 0.02,
+      "intermediate_size": 11008,
+      "vocab_size": 151936,
+      "num_attention_heads": 16,
+      "num_hidden_layers": 36,
+      "num_key_value_heads": 2,
+      "max_position_embeddings": 32768,
+      "max_window_layers": 70,
+      "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": 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,
+      "_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": "4.51.0.dev0"
+}

qwen25OmniConfig/generation_config.json

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

qwen25OmniConfig/models--Qwen--Qwen2.5-Omni-3B/refs/main

@@ -0,0 +1 @@
+f75b40e3da2003cdd6e1829b1f420ca70797c34e

qwen25OmniConfig/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
+}

qwen25OmniConfig/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|>"
+  ],
+  "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
+  },
+  "image_token": "<|IMAGE|>",
+  "audio_token": "<|AUDIO|>",
+  "video_token": "<|VIDEO|>",
+  "vision_bos_token": "<|vision_bos|>",
+  "vision_eos_token": "<|vision_eos|>",
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>"
+}

qwen25OmniConfig/spk_dict.pt

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

qwen25OmniConfig/tokenizer.json

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

qwen25OmniConfig/tokenizer_config.json

@@ -0,0 +1,223 @@
+{
+  "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": {
+    "image_token": "<|IMAGE|>",
+    "audio_token": "<|AUDIO|>",
+    "video_token": "<|VIDEO|>",
+    "vision_bos_token": "<|vision_bos|>",
+    "vision_eos_token": "<|vision_eos|>",
+    "audio_bos_token": "<|audio_bos|>",
+    "audio_eos_token": "<|audio_eos|>"
+  },
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5OmniProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "image_token": "<|IMAGE|>",
+  "audio_token": "<|AUDIO|>",
+  "video_token": "<|VIDEO|>",
+  "vision_bos_token": "<|vision_bos|>",
+  "vision_eos_token": "<|vision_eos|>",
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>"
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "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": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "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_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "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_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "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|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

upload.py

@@ -0,0 +1,46 @@
+"""Upload the sharded checkpoint folder to zhifeixie/Mini-Omni3."""
+import argparse
+from pathlib import Path
+
+from huggingface_hub import HfApi, login
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--folder", default="/Users/yansc-xzf/Desktop/工作/Mini-Omni3/github/omni3/Mini-Omni3/checkpoints")
+    ap.add_argument("--repo-id", default="zhifeixie/Mini-Omni3")
+    ap.add_argument("--path-in-repo", default=".",
+                    help="Subdirectory inside the repo. Use '.' to upload at repo root.")
+    ap.add_argument("--private", action="store_false")
+    ap.add_argument("--token", default=None,
+                    help="HF token. If omitted, uses cached login (`huggingface-cli login`).")
+    args = ap.parse_args()
+
+    if args.token:
+        login(token=args.token)
+
+    api = HfApi()
+    api.create_repo(repo_id=args.repo_id, repo_type="model",
+                    private=args.private, exist_ok=True)
+
+    folder = Path(args.folder)
+    if not folder.is_dir():
+        raise SystemExit(f"Not a directory: {folder}")
+
+    print(f"Uploading {folder} → {args.repo_id}:{args.path_in_repo}")
+    # upload_large_folder is designed for multi-GB folders: parallel chunked
+    # uploads with automatic resume on interruption.
+    api.upload_large_folder(
+        repo_id=args.repo_id,
+        repo_type="model",
+        folder_path=str(folder),
+        # path_in_repo is not directly supported by upload_large_folder;
+        # we emulate it via allow_patterns if needed. The simplest path is
+        # to upload the folder as-is at the repo root, OR to rename your
+        # local folder to match the desired in-repo name.
+    )
+    print("Done. Check: https://huggingface.co/" + args.repo_id)
+
+
+if __name__ == "__main__":
+    main()

utils.py

@@ -0,0 +1,68 @@
+"""Shard MiniOmni3_LM.pt into HF safetensors shards.
+
+Output layout (under --out-dir):
+    model-00001-of-0000N.safetensors
+    model-00002-of-0000N.safetensors
+    ...
+    model.safetensors.index.json
+"""
+import argparse
+from pathlib import Path
+
+import torch
+from huggingface_hub import save_torch_state_dict
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--ckpt", default="/Users/yansc-xzf/Desktop/工作/Mini-Omni3/github/omni3/Mini-Omni3/checkpoints/MiniOmni3_LM.pt")
+    ap.add_argument("--out-dir", default="/Users/yansc-xzf/Desktop/工作/Mini-Omni3/github/omni3/Mini-Omni3/checkpoints/")
+    ap.add_argument("--max-shard-size", default="4GB",
+                    help="HF-style size string, e.g. '4GB', '2GB', '500MB'.")
+    args = ap.parse_args()
+
+    out_dir = Path(args.out_dir)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    print(f"Loading {args.ckpt} (this loads the full ~13 GB into RAM once)…")
+    obj = torch.load(args.ckpt, map_location="cpu", weights_only=False)
+
+    # Most training scripts save either a raw state_dict, or {"model": state_dict, ...}.
+    if isinstance(obj, dict) and "model" in obj and isinstance(obj["model"], dict):
+        state_dict = obj["model"]
+        print("Detected wrapped checkpoint — using obj['model'].")
+    elif isinstance(obj, dict) and all(isinstance(v, torch.Tensor) for v in obj.values()):
+        state_dict = obj
+        print("Detected raw state_dict.")
+    else:
+        raise SystemExit(
+            f"Unexpected checkpoint structure: top-level type={type(obj)}. "
+            f"Inspect the file and adjust this script (the variable `state_dict` "
+            f"must end up as Dict[str, Tensor])."
+        )
+
+    # Safetensors can't store shared/aliased tensors silently. Clone any duplicates
+    # so save_torch_state_dict doesn't complain. Cheap when there are no aliases.
+    seen = {}
+    for k, v in list(state_dict.items()):
+        ptr = v.data_ptr()
+        if ptr in seen:
+            state_dict[k] = v.clone()
+        else:
+            seen[ptr] = k
+
+    print(f"Sharding to {out_dir} with max_shard_size={args.max_shard_size}…")
+    save_torch_state_dict(
+        state_dict=state_dict,
+        save_directory=str(out_dir),
+        max_shard_size=args.max_shard_size,
+        # filename_pattern defaults to "model-{index:05d}-of-{total:05d}.safetensors"
+    )
+    print("Done. Files written:")
+    for p in sorted(out_dir.iterdir()):
+        sz = p.stat().st_size / (1024**3)
+        print(f"  {p.name}  ({sz:.2f} GB)")
+
+
+if __name__ == "__main__":
+    main()