Upload 10 files

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

config.json

@@ -1,28 +1,36 @@
 {
-  "_name_or_path": "openbmb/MiniCPM-o-2_6",
   "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": 1024,
     "decoder_attention_heads": 16,
-    "decoder_ffn_dim": 4096,
-    "decoder_layers": 24,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 1,
     "decoder_start_token_id": 50258,
+    "dropout": 0.0,
     "encoder_attention_heads": 16,
     "encoder_ffn_dim": 4096,
-    "encoder_layers": 2,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 1,
     "eos_token_id": 50257,
     "forced_decoder_ids": [
       [
@@ -38,10 +46,22 @@
         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": 1500,
+    "max_target_positions": 448,
+    "median_filter_width": 7,
     "model_type": "whisper",
     "num_hidden_layers": 24,
+    "num_mel_bins": 80,
     "pad_token_id": 50257,
+    "scale_embedding": false,
     "suppress_tokens": [
       1,
       2,
@@ -132,7 +152,11 @@
       50361,
       50362
     ],
-    "torch_dtype": "float32"
+    "torch_dtype": "float32",
+    "use_bfloat16": true,
+    "use_cache": true,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 51865
   },
   "audio_pool_step": 2,
   "auto_map": {
@@ -146,39 +170,68 @@
   "drop_vision_last_layer": false,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 168,
+  "hidden_size": 128,
   "image_size": 448,
   "init_audio": true,
   "init_tts": true,
   "init_vision": true,
   "initializer_range": 0.02,
-  "intermediate_size": 32,
+  "intermediate_size": 16,
   "listen_speak_type": "asr",
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "minicpmo",
   "num_attention_heads": 28,
-  "num_heads": 2,
-  "num_hidden_layers": 2,
+  "num_heads": 1,
+  "num_hidden_layers": 1,
   "num_key_value_heads": 4,
   "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"
+    "model_type": "minicpmv",
+    "patch_size": 14,
+    "scale_resolution": 448
   },
   "slice_mode": true,
-  "sliding_window": null,
+  "sliding_window": 131072,
   "stream_input": false,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
   "tts_config": {
-    "hidden_size": 24,
-    "llm_dim": 32,
-    "model_type": "conditional_chattts"
+    "_attn_implementation_autoset": true,
+    "attn_implementation": "sdpa",
+    "audio_bos_token_id": 21132,
+    "aug_loss_weight": true,
+    "hidden_size": 8,
+    "intermediate_size": 4,
+    "llm_dim": 4,
+    "max_position_embeddings": 4096,
+    "model_type": "conditional_chattts",
+    "num_attention_heads": 1,
+    "num_audio_tokens": 10,
+    "num_heads": 1,
+    "num_hidden_layers": 1,
+    "num_layers": 1,
+    "num_mel_bins": 10,
+    "num_spk_embs": 1,
+    "num_text_tokens": 20,
+    "num_vq": 4,
+    "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_bfloat16": true,
+    "use_llm_hidden_state": false,
+    "use_mlp": true,
+    "use_speaker_embedding": true,
+    "use_text": true
   },
   "use_cache": true,
   "use_image_id": true,
@@ -186,11 +239,16 @@
   "version": 2.6,
   "vision_batch_size": 16,
   "vision_config": {
-    "hidden_size": 32,
-    "image_size": 224,
-    "intermediate_size": 32,
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 8,
+    "image_size": 100,
+    "intermediate_size": 8,
+    "layer_norm_eps": 1e-06,
     "model_type": "siglip_vision_model",
-    "num_attention_heads": 2,
+    "num_attention_heads": 1,
+    "num_channels": 3,
     "num_hidden_layers": 1,
     "patch_size": 14
   },

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.50.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e78bc28359ce3fdf08cfc2dc701d4903c34ebb5943e12decb3d5ce6ad9901f80
-size 410265248
+oid sha256:ef2070dfe835c58851cfdb0911b4333a20d2be6445f18b8ae14a0c7994eb34aa
+size 143909968

preprocessor_config.json

@@ -4,6 +4,7 @@
     "AutoProcessor": "openbmb/MiniCPM-o-2_6--processing_minicpmo.MiniCPMOProcessor"
   },
   "chunk_length": 30,
+  "dither": 0.0,
   "feature_extractor_type": "WhisperFeatureExtractor",
   "feature_size": 80,
   "hop_length": 160,

tokenizer_config.json

@@ -515,8 +515,10 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
+  "processor_class": "MiniCPMOProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "MiniCPMOTokenizer",
   "unk_token": "<unk>"