| { | |
| "_commit_hash": null, | |
| "architectures": [ | |
| "PVCInternVLModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_pvc_internvl.PVCInternVLConfig", | |
| "AutoModel": "modeling_pvc_internvl.PVCInternVLModel", | |
| "AutoModelForCausalLM": "modeling_pvc_internvl.PVCInternVLModel" | |
| }, | |
| "downsample_ratio": 0.25, | |
| "dynamic_image_size": true, | |
| "force_image_size": 448, | |
| "image_repeat_time": 4, | |
| "llm_config": { | |
| "_name_or_path": "internlm/internlm2_5-7b-chat", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "InternLM2ForCausalLM" | |
| ], | |
| "attn_implementation": "flash_attention_2", | |
| "auto_map": { | |
| "AutoConfig": "configuration_internlm2.InternLM2Config", | |
| "AutoModel": "modeling_internlm2.InternLM2ForCausalLM", | |
| "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM" | |
| }, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bias": false, | |
| "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": 4096, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "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": "internlm2", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 32, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 2, | |
| "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": { | |
| "factor": 2.0, | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 1000000, | |
| "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, | |
| "transformers_version": "4.43.3", | |
| "typical_p": 1.0, | |
| "use_bfloat16": true, | |
| "use_cache": true, | |
| "vocab_size": 92553 | |
| }, | |
| "max_dynamic_patch": 12, | |
| "min_dynamic_patch": 1, | |
| "mlp_add_ops": "adaln_temporal_rel", | |
| "model_type": "pvc_internvl", | |
| "pad2square": false, | |
| "ps_version": "v2", | |
| "select_layer": -1, | |
| "template": "internlm2-chat", | |
| "tile_repeat_way": "cycle", | |
| "torch_dtype": "bfloat16", | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_temporal": true, | |
| "use_thumbnail": true, | |
| "video_repeat_time": 1, | |
| "vision_config": { | |
| "architectures": [ | |
| "InternVisionTemporalModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", | |
| "AutoModel": "modeling_intern_vit_pvc.InternVisionTemporalModel" | |
| }, | |
| "drop_path_rate": 0.0, | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 448, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-06, | |
| "max_temporal_length": 96, | |
| "model_type": "intern_vit_6b", | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "patch_size": 14, | |
| "qk_normalization": false, | |
| "qkv_bias": true, | |
| "relative_timestep_scale": 100, | |
| "return_dict": true, | |
| "temporal_adaln_hidden_condition": true, | |
| "temporal_adaln_zero_init": true, | |
| "temporal_alpha_channelwise": true, | |
| "temporal_alpha_init": 0.0, | |
| "temporal_causal": true, | |
| "temporal_layer_ids": [ | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 23 | |
| ], | |
| "temporal_module_place": "after_self_attn", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.3", | |
| "use_bfloat16": true, | |
| "use_flash_attn": true | |
| } | |
| } | |