Update config.json

config.json

@@ -1,103 +1,59 @@
 {
+  "model_type": "audio-only-thinker",
+  "architectures": ["AudioOnlyThinker"],
   "auto_map": {
     "AutoModelForCausalLM": "modeling_audio_only_thinker.AudioOnlyThinker"
   },
-  "architectures": [
-  "AudioOnlyThinker"
-],
-  "audio_config": {
-    "_attn_implementation_autoset": true,
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
-    "attention_dropout": 0.0,
-    "d_model": 1280,
-    "dropout": 0.0,
-    "encoder_attention_heads": 20,
-    "encoder_ffn_dim": 5120,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 32,
-    "init_std": 0.02,
-    "max_source_positions": 1500,
-    "model_type": "qwen2_5_omni_audio_encoder",
-    "n_window": 100,
-    "num_hidden_layers": 32,
-    "num_mel_bins": 128,
-    "output_dim": 3584,
-    "scale_embedding": false
-  },
-  "audio_end_token_id": 151648,
-  "audio_start_token_id": 151647,
   "audio_token_index": 151646,
+  "audio_start_token_id": 151647,
+  "audio_end_token_id": 151648,
   "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
   "text_config": {
-    "attention_dropout": 0.0,
-    "hidden_act": "silu",
+    "model_type": "qwen2_5_omni_text",
+    "vocab_size": 152064,
     "hidden_size": 3584,
-    "init_std": 0.02,
     "intermediate_size": 18944,
-    "max_position_embeddings": 32768,
-    "max_window_layers": 28,
-    "model_type": "qwen2_5_omni_text",
     "num_attention_heads": 28,
     "num_hidden_layers": 28,
     "num_key_value_heads": 4,
-    "rms_norm_eps": 1e-06,
+    "max_position_embeddings": 32768,
+    "sliding_window": 32768,
+    "max_window_layers": 28,
+    "rope_theta": 1000000.0,
     "rope_scaling": {
-      "mrope_section": [
-        16,
-        24,
-        24
-      ],
-      "rope_type": "default",
-      "type": "default"
+      "mrope_section": [16, 24, 24],
+      "type": "default",
+      "rope_type": "default"
     },
-    "rope_theta": 1000000.0,
-    "sliding_window": 32768,
-    "tie_word_embeddings": false,
     "use_cache": true,
     "use_sliding_window": false,
-    "vocab_size": 152064
-  },
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.50.0.dev0",
-  "user_token_id": 872,
-  "video_token_index": 151656,
-  "vision_config": {
-    "_attn_implementation_autoset": true,
-    "depth": 32,
-    "embed_dim": 1280,
-    "fullatt_block_indexes": [
-      7,
-      15,
-      23,
-      31
-    ],
-    "hidden_act": "silu",
-    "hidden_size": 1280,
-    "in_channels": 3,
-    "in_chans": 3,
+    "tie_word_embeddings": false,
     "init_std": 0.02,
-    "intermediate_size": 3420,
-    "model_type": "qwen2_5_omni_vision_encoder",
-    "num_heads": 16,
-    "out_hidden_size": 3584,
-    "patch_size": 14,
-    "spatial_merge_size": 2,
-    "spatial_patch_size": 14,
-    "temporal_patch_size": 2,
-    "tokens_per_second": 25,
-    "window_size": 112
+    "rms_norm_eps": 1e-06,
+    "hidden_act": "silu",
+    "attention_dropout": 0.0
   },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652,
-  "vision_token_id": 151654
-}
+  "audio_config": {
+    "model_type": "qwen2_5_omni_audio_encoder",
+    "d_model": 1280,
+    "num_hidden_layers": 32,
+    "encoder_attention_heads": 20,
+    "encoder_ffn_dim": 5120,
+    "dropout": 0.0,
+    "activation_function": "gelu",
+    "num_mel_bins": 128,
+    "output_dim": 3584,
+    "max_source_positions": 1500,
+    "n_window": 100,
+    "scale_embedding": false,
+    "init_std": 0.02,
+    "activation_dropout": 0.0,
+    "attention_dropout": 0.0,
+    "_attn_implementation_autoset": true
+  }
+}