config.json

{
  "_name_or_path": "llava-hf/llava-1.5-7b-hf",
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_seq_length": 576,
  "image_token_index": 32000,
  "model_type": "llava",
  "pad_token_id": 32001,
  "projector_hidden_act": "gelu",
  "quantization_config": {
    "config_groups": {
      "group_1": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "symmetric": false,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "language_model.lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "text_config": {
    "_name_or_path": "lmsys/vicuna-7b-v1.5",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "rms_norm_eps": 1e-05,
    "torch_dtype": "float16",
    "vocab_size": 32064
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.47.0",
  "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": 32064
}