config.json

{
  "_name_or_path": "./Meta-Llama-3-8B-Instruct",
  "architectures": [
    "CambrianLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "connector_depth": 3,
  "connector_only": false,
  "eos_token_id": 128001,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "image_position": 91,
  "image_token_len": 576,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "sva",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_sampler_lr": null,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower_aux_list": [
    "siglip/CLIP-ViT-SO400M-14-384",
    "openai/clip-vit-large-patch14-336",
    "facebook/dinov2-giant-res378",
    "clip-convnext-XXL-multi-stage"
  ],
  "mm_vision_tower_aux_token_len_list": [
    576,
    576,
    576,
    9216
  ],
  "mm_vision_tower_lr": null,
  "model_type": "cambrian_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_of_vision_sampler_layers": 10,
  "num_query_group": 1,
  "pretraining_tp": 1,
  "query_num_list": [
    576
  ],
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "spmd_debug": null,
  "spmd_fsdp_sharding": null,
  "spmd_mesh": null,
  "start_of_vision_sampler_layers": 0,
  "stride_of_vision_sampler_layers": 3,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float32",
  "transformers_version": "4.40.1",
  "tune_mm_mlp_adapter": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vision_hidden_size": 1024,
  "vision_tower_aux_token_len_list": [
    576,
    576,
    576,
    9216
  ],
  "vocab_size": 128256
}