初始化项目，由ModelHub XC社区提供模型

Model: OpenBMB/MiniCPM-o-2_6
Source: Original Platform

config.json

@@ -0,0 +1,194 @@
+{
+  "_name_or_path": "openbmb/MiniCPM-o-2_6",
+  "architectures": [
+    "MiniCPMO"
+  ],
+
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_sliding_window": false,
+  "vocab_size": 151700,
+  "batch_vision_input": true,
+  "drop_vision_last_layer": false,
+  "image_size": 448,
+
+  "audio_chunk_length": 1.0,
+  "audio_config": {
+    "_name_or_path": "openai/whisper-medium",
+    "architectures": [
+      "MiniCPMWhisperEncoder"
+    ],
+    "begin_suppress_tokens": [
+      220,
+      50257
+    ],
+    "bos_token_id": 50257,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layers": 24,
+    "decoder_start_token_id": 50258,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layers": 24,
+    "eos_token_id": 50257,
+    "forced_decoder_ids": [
+      [
+        1,
+        50259
+      ],
+      [
+        2,
+        50359
+      ],
+      [
+        3,
+        50363
+      ]
+    ],
+    "max_length": 448,
+    "model_type": "whisper",
+    "num_hidden_layers": 24,
+    "pad_token_id": 50257,
+    "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"
+  },
+  "audio_pool_step": 2,
+  "auto_map": {
+    "AutoConfig": "configuration_minicpm.MiniCPMOConfig",
+    "AutoModel": "modeling_minicpmo.MiniCPMO",
+    "AutoModelForCausalLM": "modeling_minicpmo.MiniCPMO"
+  },
+  "chunk_input": true,
+  "listen_speak_type": "asr",
+  "model_type": "minicpmo",
+  "patch_size": 14,
+  "query_num": 64,
+  "slice_config": {
+    "max_slice_nums": 9,
+    "model_type": "minicpmv"
+  },
+  "slice_mode": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "tts_config": {
+    "model_type": "conditional_chattts",
+    "llm_dim": 3584
+  },
+  "use_cache": true,
+  "use_image_id": true,
+  "version": 2.6,
+  "vision_batch_size": 16,
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}