| { | |
| "_name_or_path": "/home/ubuntu/deepfake/VideoLLaMA3/trained_model/deepfake/stage5", | |
| "architectures": [ | |
| "Videollama3Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "DAMO-NLP-SG/VideoLLaMA3-7B--configuration_videollama3.Videollama3Qwen2Config", | |
| "AutoModelForCausalLM": "DAMO-NLP-SG/VideoLLaMA3-7B--modeling_videollama3.Videollama3Qwen2ForCausalLM" | |
| }, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_aspect_ratio": "square", | |
| "image_size": -1, | |
| "image_token_index": 151665, | |
| "image_token_length": 1, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "is_alignment": false, | |
| "llm_lr": 1e-05, | |
| "max_frames": 60, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "mm_hidden_size": 1152, | |
| "mm_projector_lr": 1e-05, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_vision_encoder": "DAMO-NLP-SG/SigLIP-NaViT", | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -1, | |
| "model_type": "videollama3_qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 16384, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "use_sliding_window": false, | |
| "use_token_compression": true, | |
| "vision_encoder": "DAMO-NLP-SG/SigLIP-NaViT", | |
| "vision_encoder_config": { | |
| "_attn_implementation_autoset": false, | |
| "_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": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "intermediate_size": 4304, | |
| "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": "videollama3_vision_encoder", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_return_sequences": 1, | |
| "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, | |
| "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 | |
| }, | |
| "vision_encoder_lr": 2e-06, | |
| "vocab_size": 152064 | |
| } | |