{ "_name_or_path": "multimodal-tinyllama-whisper-small-siglip/checkpoint-450", "architectures": [ "MM_LLMs" ], "attention_heads": 8, "audio_config": { "_name_or_path": "mesolitica/malaysian-whisper-small", "activation_dropout": 0.0, "activation_function": "gelu", "add_cross_attention": false, "apply_spec_augment": false, "architectures": [ "WhisperForConditionalGeneration" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": [ 220, 50257 ], "bos_token_id": 50257, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "cross_attention_hidden_size": null, "d_model": 768, "decoder_attention_heads": 12, "decoder_ffn_dim": 3072, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 50258, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.0, "early_stopping": false, "encoder_attention_heads": 12, "encoder_ffn_dim": 3072, "encoder_layerdrop": 0.0, "encoder_layers": 12, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 50257, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_decoder_ids": [ [ 1, 50259 ], [ 2, 50359 ], [ 3, 50363 ] ], "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_std": 0.02, "is_decoder": false, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "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, "min_length": 0, "model_type": "whisper", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 12, "num_mel_bins": 80, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 50257, "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": [ 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, 50360, 50361, 50362 ], "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": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_weighted_layer_sum": false, "vocab_size": 51865 }, "audio_conv_kernel": 240, "audio_conv_stride": 220, "auto_map": { "AutoConfig": "modeling.MM_LLMs_Config", "AutoModel": "modeling.MM_LLMs" }, "hidden_size": 2048, "image_config": { "_name_or_path": "google/siglip-base-patch16-224", "add_cross_attention": false, "architectures": [ "SiglipModel" ], "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" }, "initializer_factor": 1.0, "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": "siglip", "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, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "text_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 49406, "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": 49407, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 64, "min_length": 0, "model_type": "siglip_text_model", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 1, "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, "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, "vocab_size": 32000 }, "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, "vision_config": { "_name_or_path": "", "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, "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, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 224, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "siglip_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 16, "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, "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 } }, "image_conv_kernel": 48, "image_conv_stride": 36, "llm_config": { "_name_or_path": "mesolitica/malaysian-tinyllama-1.1b-16k-instructions-v3", "add_cross_attention": false, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "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": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 5632, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "min_length": 0, "model_type": "llama", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 22, "num_key_value_heads": 4, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "pretraining_tp": 1, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "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": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32004 }, "model_type": "mm_llms", "n_frames": 6, "torch_dtype": "bfloat16", "transformers_version": "4.37.1" }