| { |
| "anyres": false, |
| "architectures": [ |
| "HCXVisionV2ForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_vlm.HCXVisionConfig", |
| "AutoModelForCausalLM": "modeling_vlm.HCXVisionForCausalLM", |
| "AutoModelForSequenceClassification": "modeling_vlm.HCXVisionForSequenceClassification", |
| "AutoModelForTokenClassification": "modeling_vlm.HCXVisionForTokenClassification" |
| }, |
| "bos_token_id": 0, |
| "eos_token_id": 128001, |
| "freeze_before_sampler": false, |
| "freeze_decoder": false, |
| "freeze_encoder": true, |
| "freeze_mm_projector": false, |
| "hidden_size": 5120, |
| "ignore_index": -100, |
| "image_token_id": 128060, |
| "img_start_id": 128060, |
| "is_safetensor_save": true, |
| "max_num_grids": -1, |
| "mm_projector_type": "linear", |
| "model_type": "hyperclovax_vision_v2", |
| "num_queries_vis_abstractor": -1, |
| "pad_token_id": 0, |
| "possible_resolutions": [], |
| "proj_pos_emb": true, |
| "proj_prenorm": false, |
| "q_former_model_name_or_path": null, |
| "text_config": { |
| "add_cross_attention": false, |
| "architectures": [ |
| "HyperCLOVAXForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_multiplier": 0.08838834764831845, |
| "auto_map": { |
| "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig", |
| "AutoModel": "modeling_hyperclovax.HyperCLOVAXModel", |
| "AutoModelForCausalLM": "modeling_hyperclovax.HyperCLOVAXForCausalLM" |
| }, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 128000, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "early_stopping": false, |
| "embedding_multiplier": 1.0, |
| "encoder_no_repeat_ngram_size": 0, |
| "end_token_id": 128001, |
| "eos_token_id": 128001, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.006, |
| "intermediate_size": 24192, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "logits_scaling": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 131072, |
| "min_length": 0, |
| "mlp_bias": false, |
| "model_type": "hyperclovax", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 40, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 72, |
| "num_key_value_heads": 8, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 0, |
| "prefix": null, |
| "pretraining_tp": 1, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "resid_pdrop": 0.2, |
| "residual_multiplier": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 50000000, |
| "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": "float32", |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": false, |
| "use_post_norm": false, |
| "vocab_size": 128256, |
| "_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B" |
| }, |
| "text_model_name_or_path": null, |
| "torch_dtype": "float32", |
| "transformers_version": "4.52.4", |
| "unpad": false, |
| "use_1x1_grid": false, |
| "use_nth_layer": -2, |
| "video_first_last_frames_slows": null, |
| "video_max_num_frames": null, |
| "video_num_queries_fast": null, |
| "video_num_queries_slow": null, |
| "video_start_id": 128061, |
| "video_token_id": 128061, |
| "vision_config": { |
| "add_cross_attention": false, |
| "anyres": false, |
| "architectures": [ |
| "Qwen2_5_VisionTransformerPretrainedModel" |
| ], |
| "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" |
| }, |
| "in_channels": 3, |
| "in_chans": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 3456, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_num_grids": -1, |
| "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": 5120, |
| "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, |
| "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": true, |
| "tokenizer_class": null, |
| "tokens_per_second": 2, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torch_dtype": "float32", |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "window_size": 112 |
| }, |
| "vision_input_chunk_size": null, |
| "vision_model_name_or_path": null |
| } |
