config.json

{
  "architectures": [
    "MiniCPMO"
  ],
  "attention_dropout": 0.0,
  "audio_chunk_length": 1.0,
  "audio_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "openai/whisper-medium",
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "apply_spec_augment": false,
    "architectures": [
      "MiniCPMWhisperEncoder"
    ],
    "attention_dropout": 0.0,
    "begin_suppress_tokens": [
      220,
      50257
    ],
    "bos_token_id": 50257,
    "classifier_proj_size": 256,
    "d_model": 64,
    "decoder_attention_heads": 4,
    "decoder_ffn_dim": 128,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 1,
    "decoder_start_token_id": 50258,
    "dropout": 0.0,
    "encoder_attention_heads": 4,
    "encoder_ffn_dim": 128,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 1,
    "eos_token_id": 50257,
    "forced_decoder_ids": [
      [
        1,
        50259
      ],
      [
        2,
        50359
      ],
      [
        3,
        50363
      ]
    ],
    "init_std": 0.02,
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_prob": 0.05,
    "max_length": 448,
    "max_source_positions": 100,
    "max_target_positions": 100,
    "median_filter_width": 7,
    "model_type": "whisper",
    "num_hidden_layers": 1,
    "num_mel_bins": 20,
    "pad_token_id": 50257,
    "scale_embedding": false,
    "suppress_tokens": [
      1,
      2,
      7,
      8,
      9,
      10,
      14,
      25,
      26,
      27,
      28,
      29,
      31,
      58,
      59,
      60,
      61,
      62,
      63,
      90,
      91,
      92,
      93,
      359,
      503,
      522,
      542,
      873,
      893,
      902,
      918,
      922,
      931,
      1350,
      1853,
      1982,
      2460,
      2627,
      3246,
      3253,
      3268,
      3536,
      3846,
      3961,
      4183,
      4667,
      6585,
      6647,
      7273,
      9061,
      9383,
      10428,
      10929,
      11938,
      12033,
      12331,
      12562,
      13793,
      14157,
      14635,
      15265,
      15618,
      16553,
      16604,
      18362,
      18956,
      20075,
      21675,
      22520,
      26130,
      26161,
      26435,
      28279,
      29464,
      31650,
      32302,
      32470,
      36865,
      42863,
      47425,
      49870,
      50254,
      50258,
      50358,
      50359,
      50360,
      50361,
      50362
    ],
    "torch_dtype": "float32",
    "use_cache": true,
    "use_weighted_layer_sum": false,
    "vocab_size": 1000
  },
  "audio_pool_step": 2,
  "auto_map": {
    "AutoConfig": "openbmb/MiniCPM-o-2_6--configuration_minicpm.MiniCPMOConfig",
    "AutoModel": "openbmb/MiniCPM-o-2_6--modeling_minicpmo.MiniCPMO",
    "AutoModelForCausalLM": "openbmb/MiniCPM-o-2_6--modeling_minicpmo.MiniCPMO"
  },
  "batch_vision_input": true,
  "bos_token_id": 4901,
  "chunk_input": true,
  "drop_vision_last_layer": false,
  "eos_token_id": 4903,
  "hidden_act": "silu",
  "hidden_size": 128,
  "image_size": 448,
  "init_audio": true,
  "init_tts": true,
  "init_vision": true,
  "initializer_range": 0.02,
  "intermediate_size": 256,
  "listen_speak_type": "asr",
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "minicpmo",
  "num_attention_heads": 8,
  "num_hidden_layers": 1,
  "num_key_value_heads": 2,
  "patch_size": 14,
  "query_num": 64,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "slice_config": {
    "max_slice_nums": 9,
    "model_type": "minicpmv",
    "patch_size": 14,
    "scale_resolution": 448
  },
  "slice_mode": true,
  "sliding_window": 131072,
  "stream_input": false,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "tts_config": {
    "_attn_implementation_autoset": true,
    "attn_implementation": "sdpa",
    "audio_bos_token_id": 21132,
    "aug_loss_weight": true,
    "hidden_size": 128,
    "intermediate_size": 256,
    "llm_dim": 128,
    "max_position_embeddings": 256,
    "model_type": "conditional_chattts",
    "num_attention_heads": 8,
    "num_audio_tokens": 10,
    "num_hidden_layers": 1,
    "num_mel_bins": 10,
    "num_spk_embs": 1,
    "num_text_tokens": 100,
    "num_vq": 1,
    "spk_emb_token_id": 21143,
    "streaming": true,
    "streaming_audio_chunk_size": 50,
    "streaming_text_chunk_size": 10,
    "streaming_text_reserved_len": 300,
    "text_eos_token_id": 21133,
    "use_llm_hidden_state": false,
    "use_mlp": true,
    "use_speaker_embedding": true,
    "use_text": true
  },
  "use_cache": true,
  "use_image_id": true,
  "use_sliding_window": false,
  "version": 2.6,
  "vision_batch_size": 16,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 128,
    "image_size": 980,
    "intermediate_size": 256,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 8,
    "num_channels": 3,
    "num_hidden_layers": 1,
    "patch_size": 14
  },
  "vocab_size": 5000
}