config.json

{
  "_name_or_path": "HuggingFaceM4/idefics-9b-instruct",
  "additional_vocab_size": 3,
  "alpha_initializer": "zeros",
  "alpha_type": "float",
  "alphas_initializer_range": 0.0,
  "architectures": [
    "IdeficsForVisionText2Text"
  ],
  "bos_token_id": 1,
  "cross_layer_activation_function": "swiglu",
  "cross_layer_interval": 4,
  "dropout": 0.0,
  "eos_token_id": 2,
  "freeze_lm_head": false,
  "freeze_text_layers": false,
  "freeze_text_module_exceptions": [],
  "freeze_vision_layers": false,
  "freeze_vision_module_exceptions": [],
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 2048,
  "max_sequence_length": 2048,
  "model_type": "idefics",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "pad_token_id": 0,
  "perceiver_config": {
    "model_type": "idefics",
    "qk_layer_norms_perceiver": true
  },
  "qk_layer_norms": true,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "float16",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head",
      "embed_tokens"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.38.2",
  "use_cache": true,
  "use_resampler": true,
  "vision_config": {
    "embed_dim": 1280,
    "model_type": "idefics"
  },
  "vocab_size": 32000
}