monkey_model/config.json

{
    "architectures": [
      "MonkeyLMHeadModel"
    ],
    "attn_dropout_prob": 0.0,
    "auto_map": {
      "AutoConfig": "configuration_qwen.QWenConfig",
      "AutoModelForCausalLM": "modeling_monkey.MonkeyLMHeadModel"
    },
    "bf16": true,
    "emb_dropout_prob": 0.0,
    "fp16": false,
    "fp32": false,
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 22016,
    "kv_channels": 128,
    "layer_norm_epsilon": 1e-06,
    "max_position_embeddings": 8192,
    "model_type": "monkey",
    "no_bias": true,
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "onnx_safe": null,
    "rotary_emb_base": 10000,
    "rotary_pct": 1.0,
    "scale_attn_weights": true,
    "seq_length": 2048,
    "tie_word_embeddings": false,
    "tokenizer_type": "QWenTokenizer",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.32.0",
    "use_cache": false,
    "use_dynamic_ntk": true,
    "use_flash_attn": false,
    "use_logn_attn": true,
    "visual": {
      "heads": 16,
      "image_size": 896,
      "image_start_id": 151857,
      "layers": 48,
      "mlp_ratio": 4.9231,
      "output_dim": 4096,
      "patch_size": 14,
      "width": 1664,
      "lora_repeat_num":4
    },
    "vocab_size": 151936
  }