config.json

{
  "anyres": true,
  "architectures": [
    "HCXVisionForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_hyperclovax.HCXVisionConfig",
    "AutoModelForCausalLM": "modeling_hyperclovax.HCXVisionForCausalLM"
  },
  "decoder_max_length": 16384,
  "freeze_decoder": false,
  "freeze_encoder": true,
  "freeze_mm_projector": false,
  "hidden_size": 3072,
  "ignore_index": -100,
  "video_token_id": 100270,
  "image_token_id": 100271,
  "mm_projector_type": "cabstractor",
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 100257,
    "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,
    "end_token_id": 100257,
    "eos_token_id": 100257,
    "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": 3072,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 7168,
    "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": "llama",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 24,
    "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": 100257,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "resid_pdrop": 0.2,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 100000000,
    "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,
    "transformers_version": "4.52.4",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 110592
  },
  "max_image_cnt": 12,
  "max_num_grids": 9,
  "model_type": "hyperclovax_vlm",
  "num_queries_vis_abstractor_image": 81,
  "num_queries_vis_abstractor_video_slow": 81,
  "num_queries_vis_abstractor_video_fast": 9,
  "first_last_frames_slow": false,
  "proj_pos_emb": true,
  "proj_prenorm": false,
  "q_former_model_name_or_path": null,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.4",
  "unpad": true,
  "use_1x1_grid": true,
  "use_nth_layer": -2,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "SiglipVisionModel"
    ],
    "attention_dropout": 0.0,
    "auto_map": {},
    "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"
    },
    "image_size": 378,
    "initializer_factor": 1.0,
    "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,
    "max_num_grids": 9,
    "min_length": 0,
    "model_type": "siglip_vision_model",
    "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": "bfloat16",
    "torchscript": false,
    "transformers_version": "4.52.4",
    "typical_p": 1.0,
    "use_bfloat16": true
  }
}