| { | |
| "architectures": [ | |
| "ApolloForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "flash_attention_2", | |
| "clip_duration": 2, | |
| "drop_path_rate": 0.0, | |
| "encode_batch_size": 25, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "image_aspect_ratio": "square", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "interpolate_mode": "linear", | |
| "llm_cfg": { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 151643, | |
| "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": 151645, | |
| "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": 11008, | |
| "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": 70, | |
| "min_length": 0, | |
| "model_max_length": 16384, | |
| "model_type": "qwen2", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 2, | |
| "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, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sep_token_id": null, | |
| "sliding_window": 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, | |
| "tokenizer_model_max_length": 16384, | |
| "tokenizer_padding_side": "right", | |
| "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, | |
| "vocab_size": 151936 | |
| }, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "mm_connector_cfg": { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Connector" | |
| ], | |
| "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, | |
| "ff_multi": 4, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "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": "mm_connector", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_key_value_heads": 4, | |
| "num_output_tokens": 128, | |
| "num_patches": 24, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "projector_type": "mlp1x_gelu", | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "resampler_depth": 1, | |
| "resampler_head_dim": 96, | |
| "resampler_n_heads": 16, | |
| "resampler_type": "perciver", | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "text_hidden_size": 2048, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "token_input_shape": [ | |
| 4, | |
| 27, | |
| 27 | |
| ], | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vision_hidden_size": 2560 | |
| }, | |
| "mm_connector_lr": 0.0001, | |
| "mm_hidden_size": null, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "model_dtype": "torch.bfloat16", | |
| "model_type": "apollo", | |
| "num_attention_heads": 16, | |
| "num_encode_batch": 0, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 2, | |
| "num_video_frames": null, | |
| "resume_path": "./work_dirs/final_run/apollo-Qwen2.5-3B-Instruct-internvideo2-siglip-so400m-patch14-384-freeze-perciver_128_2-newprompt-ft", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "s2": false, | |
| "s2_max_split_size": 336, | |
| "s2_scales": "336,672,1008", | |
| "sliding_window": null, | |
| "temporal_prompt": true, | |
| "timestamp_prompt": true, | |
| "transformers_version": "4.44.0", | |
| "tune_language_model": true, | |
| "tune_mm_connector": true, | |
| "tune_vision_tower": false, | |
| "use_cache": true, | |
| "use_mm_patch_token": false, | |
| "use_mm_start_end": false, | |
| "use_sliding_window": false, | |
| "vision_resolution": -1, | |
| "vision_tower_cfg": { | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "configs": {}, | |
| "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" | |
| }, | |
| "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": "hybrid_vision_tower", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "num_vision_encoders": 2, | |
| "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, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "token_output_shape": [ | |
| 4, | |
| 27, | |
| 27 | |
| ], | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vision_towers": [ | |
| "siglip-so400m-patch14-384", | |
| "internvideo2" | |
| ] | |
| }, | |
| "vocab_size": 151936, | |
| "auto_map": { | |
| "AutoConfig": "configuration_apollo.ApolloConfig", | |
| "AutoModelForCausalLM": "modeling_apollo.ApolloForCausalLM" | |
| }, | |
| "model_max_length": 16384 | |
| } |