| { | |
| "architectures": [ | |
| "NamoForCausalLM" | |
| ], | |
| "audio_config": { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "attention_dropout": 0.0, | |
| "classifier_proj_size": 256, | |
| "d_model": 384, | |
| "decoder_attention_heads": 6, | |
| "decoder_ffn_dim": 1536, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 4, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 6, | |
| "encoder_ffn_dim": 1536, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 4, | |
| "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_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "median_filter_width": 7, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 4, | |
| "num_mel_bins": 80, | |
| "scale_embedding": false, | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51865 | |
| }, | |
| "conn_ve_llm_lr": 1e-05, | |
| "conn_ve_llm_type": "glu", | |
| "dynamic_size": false, | |
| "freeze_conn_ve_llm": false, | |
| "ignore_index": -100, | |
| "image_aspect_ratio": "pad", | |
| "image_seq_length": 576, | |
| "image_token_index": -200, | |
| "longest_edge": null, | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "model_type": "namo", | |
| "multimodal_projector_bias": true, | |
| "new_img_size": null, | |
| "num_patches": 1024, | |
| "num_visual_tokens": 578, | |
| "s2": false, | |
| "s2_max_split_size": 384, | |
| "s2_scales": "384,768", | |
| "shortest_edge": null, | |
| "text_config": { | |
| "_name_or_path": "checkpoints/Qwen3-4B", | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "tokenizer_model_max_length": 131072, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.2", | |
| "tune_conn_ve_llm": false, | |
| "unfreeze_ve": true, | |
| "use_cache": true, | |
| "use_dft": true, | |
| "video_fps": 1, | |
| "video_frames_num": 16, | |
| "vision_config": { | |
| "_name_or_path": "checkpoints/qwen2.5-vl-7b-instruct-ve", | |
| "architectures": [ | |
| "Qwen2_5_VisionTransformerPretrainedModel" | |
| ], | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "image_token_id": 151655, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 3584, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "text_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Qwen2_5_VisionTransformerPretrainedModel" | |
| ], | |
| "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, | |
| "depth": 32, | |
| "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, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_token_id": null, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "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, | |
| "max_window_layers": 80, | |
| "min_length": 0, | |
| "model_type": "qwen2_5_vl_text", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 64, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_heads": 16, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "out_hidden_size": 3584, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "prefix": null, | |
| "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": 1000000.0, | |
| "sep_token_id": null, | |
| "sliding_window": 4096, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "temporal_patch_size": 2, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "tokens_per_second": 2, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": null, | |
| "vocab_size": 152064, | |
| "window_size": 112 | |
| }, | |
| "tokens_per_second": 2, | |
| "torch_dtype": "bfloat16", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "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, | |
| "depth": 32, | |
| "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, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "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": "qwen2_5_vl", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_heads": 16, | |
| "num_return_sequences": 1, | |
| "out_hidden_size": 3584, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "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, | |
| "spatial_merge_size": 2, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "temporal_patch_size": 2, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "tokens_per_second": 4, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "window_size": 112 | |
| }, | |
| "window_size": 112 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "same" | |
| } | |