config.json

{
    "architectures": [
        "BunnyLlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_bunny_llama.BunnyLlamaConfig",
        "AutoModelForCausalLM": "modeling_bunny_llama.BunnyLlamaForCausalLM"
    },
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "freeze_mm_mlp_adapter": false,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "image_aspect_ratio": "pad",
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "mm_hidden_size": 1152,
    "mm_projector_lr": 1e-05,
    "mm_projector_type": "mlp2x_gelu",
    "mm_vision_tower": "google/siglip-so400m-patch14-384",
    "model_type": "bunny-llama",
    "language_model": "meta-llama/Meta-Llama-3-8B",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "tie_word_embeddings": false,
    "tokenizer_model_max_length": 2048,
    "tokenizer_padding_side": "right",
    "torch_dtype": "float16",
    "transformers_version": "4.40.0",
    "tune_mm_mlp_adapter": false,
    "unfreeze_vision_tower": true,
    "use_cache": true,
    "use_mm_proj": true,
    "vision_config": {
        "intermediate_size": 4352
    },
    "vocab_size": 128256
}