{
  "_hidden_size": 4096,
  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
  "architectures": [
    "HaploLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "class_token": false,
  "eos_token_id": 128009,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "anyres_max_6",
  "image_grid_pinpoints": "(1x1),...,(2x3)",
  "image_newline": true,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "meformer": {
    "_name_or_path": "",
    "act": "gelu",
    "add_cross_attention": false,
    "architectures": null,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "class_token": false,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "depth": 24,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "embed_dim": 1024,
    "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,
    "global_pool": "",
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_aspect_ratio": "anyres_max_6",
    "image_grid_pinpoints": "(1x1),...,(2x3)",
    "image_newline": true,
    "img_size": 336,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "llm_hidden_size": 4096,
    "llm_pad_token_id": null,
    "llm_vocab_size": 128256,
    "logit_scale": "learnable",
    "max_length": 20,
    "max_position_embeddings": 8192,
    "min_length": 0,
    "mlp_ratio": 4.0,
    "mm_newline_position": "one_token",
    "mm_patch_merge_type": "spatial_unpad_nobase",
    "model_type": "early_fusion_transformer",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_heads": 16,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_dim": 768,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_drop_rate": 0.0,
    "patch_size": 14,
    "pre_norm": true,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "remove_pos_embed": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rope_base": 500000.0,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "text_only": false,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "tokenizer_model_max_length": 1000000000000000019884624838656,
    "tokenizer_pad_token_id": 128002,
    "tokenizer_padding_side": "right",
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "mm_newline_position": "one_token",
  "mm_patch_merge_type": "spatial_unpad_nobase",
  "model_type": "haplo_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.2",
  "use_cache": true,
  "vision_bimask": true,
  "vocab_size": 128256
}