config.json

{
    "architectures": [
        "LlavaNextForConditionalGeneration"
    ],
    "ignore_index": -100,
    "image_grid_pinpoints": [
        [
            336,
            672
        ],
        [
            672,
            336
        ],
        [
            672,
            672
        ],
        [
            1008,
            336
        ],
        [
            336,
            1008
        ]
    ],
    "image_token_index": 64000,
    "model_type": "llava_next",
    "projector_hidden_act": "gelu",
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "text_config": {
        "_name_or_path": "NousResearch/Nous-Hermes-2-Yi-34B",
        "architectures": [
            "LlamaForCausalLM"
        ],
        "eos_token_id": 7,
        "hidden_size": 7168,
        "intermediate_size": 20480,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "rms_norm_eps": 1e-05,
        "rope_theta": 5000000.0,
        "torch_dtype": "bfloat16",
        "use_cache": false,
        "vocab_size": 64064
    },
    "torch_dtype": "float16",
    "transformers_version": "4.39.0.dev0",
    "use_image_newline_parameter": true,
    "vision_config": {
        "hidden_size": 1024,
        "image_size": 336,
        "intermediate_size": 4096,
        "model_type": "clip_vision_model",
        "num_attention_heads": 16,
        "num_hidden_layers": 24,
        "patch_size": 14,
        "projection_dim": 768,
        "vocab_size": 32000
    },
    "vision_feature_layer": -2,
    "vision_feature_select_strategy": "default",
    "vocab_size": 64064
}