config.json

{
  "_name_or_path": "llava-1.5-7b-hf-awq",
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_token_index": 32000,
  "model_type": "llava",
  "pad_token_id": 32001,
  "projector_hidden_act": "gelu",
  "quantizaion_config": {
    "backend": "autoawq",
    "bits": 4,
    "do_fuse": false,
    "fuse_max_seq_len": null,
    "group_size": 128,
    "modules_to_fuse": null,
    "modules_to_not_convert": null,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "modules_to_not_convert": [
      "vision_tower",
      "multi_modal_projector"
    ],
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "text_config": {
    "_name_or_path": "meta-llama/Llama-2-7b-hf",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "rms_norm_eps": 1e-05,
    "torch_dtype": "float16",
    "vocab_size": 32064
  },
  "torch_dtype": "float16",
  "transformers_version": "4.36.0.dev0",
  "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
}