| { |
| "Ubit": 100, |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "IHP-Lab/AF3_PCLM_DPO", |
| "architectures": [ |
| "LlavaLlamaModel" |
| ], |
| "babit": "E5M2", |
| "bobit": "E5M2", |
| "bwbit": "E5M2", |
| "chat_template": "qwen2", |
| "col_blocksize": -1, |
| "col_blocksize_optimizer": 128, |
| "draw_distribution_backward": false, |
| "draw_distribution_forward": false, |
| "drop_path_rate": 0.0, |
| "dynamic_s2": true, |
| "epsilon": 1e-10, |
| "epsilon_optimizer": 1e-15, |
| "expose_layers": [ |
| 5, |
| 15, |
| 25, |
| 30 |
| ], |
| "fabit": "E4M3", |
| "first_order_bit": null, |
| "first_order_quant_type": null, |
| "fobit": "E4M3", |
| "fps": null, |
| "fwbit": "E4M3", |
| "group_size": -1, |
| "hidden_size": 3584, |
| "image_aspect_ratio": "dynamic_s2", |
| "image_encoder": { |
| "_target_": "llava.model.encoders.BasicImageEncoder" |
| }, |
| "interpolate_mode": "linear", |
| "llm_cfg": { |
| "_attn_implementation_autoset": false, |
| "_name_or_path": "/wekafs/ict/pangj/voxparadox/af3/audio-flamingo/runs/train/stage5_af3_ws4_para_dpo9/tmp-checkpoint-200/llm", |
| "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": 3584, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "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": 28, |
| "min_length": 0, |
| "model_max_length": 8192, |
| "model_type": "qwen2", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 28, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 28, |
| "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, |
| "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_scaling": null, |
| "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": 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": false, |
| "use_sliding_window": false, |
| "vocab_size": 151672 |
| }, |
| "max_tiles": 12, |
| "min_blockunit_col": 4, |
| "min_blockunit_row": 4, |
| "min_tiles": 1, |
| "mlp_path": null, |
| "mm_hidden_size": null, |
| "mm_projector": "mlp_downsample", |
| "mm_projector_cfg": "mlp_downsample", |
| "mm_projector_lr": null, |
| "mm_use_im_patch_token": false, |
| "mm_use_im_start_end": false, |
| "mm_vision_select_feature": "cls_patch", |
| "mm_vision_select_layer": -2, |
| "model_dtype": "torch.bfloat16", |
| "model_name_or_path": "/wekafs/ict/pangj/voxparadox/af3/audio-flamingo/runs/train/stage5_af3_ws4_sc+as+para2_5_15_25_30_pclm_fullft9", |
| "model_type": "llava_llama", |
| "num_time_tokens": 0, |
| "num_video_frames": null, |
| "pad_block": false, |
| "pad_to_multiple_of": 0, |
| "pclm_exclude_final": false, |
| "probe_run_id": null, |
| "probe_save_dir": "./probing/probing_results/probe_dumps/tensors", |
| "probing": false, |
| "qchoice": "none", |
| "quantize_model": false, |
| "refine_attn_blocksize": false, |
| "refine_col_blocksize": 4, |
| "refine_ln_blocksize": false, |
| "refine_ln_blocksize_but_only_backward": false, |
| "refine_ln_blocksize_but_only_forward": false, |
| "refine_ln_pertoken": false, |
| "refine_mlp_blocksize": false, |
| "refine_residual_fp": false, |
| "refine_row_blocksize": 4, |
| "resume_path": "/wekafs/ict/pangj/voxparadox/af3/audio-flamingo/runs/train/stage5_af3_ws4_sc+as+para2_5_15_25_30_pclm_fullft9", |
| "row_blocksize": -1, |
| "row_blocksize_optimizer": 1, |
| "s2": false, |
| "s2_max_split_size": 448, |
| "s2_resize_output_to_scale_idx": -1, |
| "s2_scales": "448,896,1344", |
| "second_order_bit": null, |
| "second_order_quant_type": null, |
| "soft_ce_std": 1.0, |
| "sound_encoder": { |
| "_target_": "llava.model.encoders.BasicSoundEncoder" |
| }, |
| "sound_hidden_size": 1280, |
| "sound_mid_mm_projector_lr": null, |
| "sound_mm_projector": "mlp", |
| "sound_mm_projector_cfg": { |
| "_attn_implementation_autoset": false, |
| "_name_or_path": "/wekafs/ict/pangj/voxparadox/af3/audio-flamingo/runs/train/stage5_af3_ws4_para_dpo9/tmp-checkpoint-200/sound_mm_projector", |
| "add_cross_attention": false, |
| "architectures": [ |
| "SoundMultimodalProjector" |
| ], |
| "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" |
| }, |
| "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": "sound_mm_projector", |
| "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, |
| "sound_mm_projector_type": "mlp", |
| "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": "bfloat16", |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| }, |
| "sound_mm_projector_lr": null, |
| "sound_pclm_text_model": "prajjwal1/bert-small", |
| "sound_tower": "openai/whisper-large-v3", |
| "sound_tower_cfg": { |
| "_attn_implementation_autoset": false, |
| "_name_or_path": "/wekafs/ict/pangj/voxparadox/af3/audio-flamingo/runs/train/stage5_af3_ws4_para_dpo9/tmp-checkpoint-200/sound_tower", |
| "activation_dropout": 0.0, |
| "activation_function": "gelu", |
| "add_cross_attention": false, |
| "apply_spec_augment": false, |
| "architectures": [ |
| "AFWhisperEncoder" |
| ], |
| "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": 1280, |
| "decoder_attention_heads": 20, |
| "decoder_ffn_dim": 5120, |
| "decoder_layerdrop": 0.0, |
| "decoder_layers": 32, |
| "decoder_start_token_id": 50258, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dropout": 0.0, |
| "early_stopping": false, |
| "encoder_attention_heads": 20, |
| "encoder_ffn_dim": 5120, |
| "encoder_layerdrop": 0.0, |
| "encoder_layers": 32, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 50257, |
| "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" |
| }, |
| "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": "qwen2_audio_encoder", |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 32, |
| "num_mel_bins": 128, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 50256, |
| "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": 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": "bfloat16", |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "use_weighted_layer_sum": false, |
| "vocab_size": 51866 |
| }, |
| "sound_tower_lr": null, |
| "speech_encoder": { |
| "_target_": "llava.model.encoders.BasicSpeechEncoder" |
| }, |
| "speech_hidden_size": null, |
| "speech_mm_projector": "mlp", |
| "speech_mm_projector_cfg": "mlp", |
| "speech_mm_projector_lr": null, |
| "speech_tower": "openai/whisper-large-v2", |
| "speech_tower_cfg": "openai/whisper-large-v2", |
| "speech_tower_lr": null, |
| "symm": true, |
| "time_token_format": "<t{t}>", |
| "time_token_ids": [], |
| "transformers_version": "4.46.0", |
| "tune_language_model": true, |
| "tune_mm_projector": false, |
| "tune_sound_mid_mm_projector": false, |
| "tune_sound_mm_projector": false, |
| "tune_sound_pclm": false, |
| "tune_sound_tower": false, |
| "tune_speech_mm_projector": false, |
| "tune_speech_tower": false, |
| "tune_vision_tower": false, |
| "use_quantize_optimizer": false, |
| "use_sound_pclm": true, |
| "version": "auto", |
| "video_encoder": { |
| "_target_": "llava.model.encoders.BasicVideoEncoder" |
| }, |
| "video_max_tiles": 1, |
| "vision_resolution": -1, |
| "vision_tower": "Efficient-Large-Model/paligemma-siglip-so400m-patch14-448", |
| "vision_tower_cfg": "Efficient-Large-Model/paligemma-siglip-so400m-patch14-448", |
| "vision_tower_lr": null, |
| "weight_memory_efficient": true |
| } |
