config.json

{
  "_name_or_path": "./checkpoints/llava-qwen-2b-otherdata-V",
  "architectures": [
    "MoELLaVAQWenForCausalLM"
  ],
  "attn_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "Qwen/Qwen-1_8B--configuration_qwen.QWenConfig",
    "AutoModelForCausalLM": "Qwen/Qwen-1_8B--modeling_qwen.QWenLMHeadModel"
  },
  "bf16": false,
  "emb_dropout_prob": 0.0,
  "fp16": true,
  "fp32": false,
  "freeze_mm_mlp_adapter": false,
  "hidden_size": 2048,
  "image_aspect_ratio": "pad",
  "image_projector_type": "mlp2x_gelu",
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "kv_channels": 128,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 8192,
  "mm_hidden_size": 1024,
  "mm_image_tower": "openai/clip-vit-large-patch14-336",
  "mm_projector_lr": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_video_tower": null,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "model_type": "moe_llava_qwen",
  "moe": {
    "capacity_factor": 1.0,
    "ep_size": 1,
    "eval_capacity_factor": 2.0,
    "min_capacity": 0,
    "moe_enable": true,
    "moe_layers_idx": [
      0,
      2,
      4,
      6,
      8,
      10,
      12,
      14,
      16,
      18,
      20,
      22
    ],
    "moe_mode": "sparse",
    "num_experts": [
      4,
      4,
      4,
      4,
      4,
      4,
      4,
      4,
      4,
      4,
      4,
      4
    ],
    "router_aux_loss_coef": 0.01,
    "top_k_experts": 2,
    "train_modules": [
      "mlp.w1",
      "mlp.w2",
      "mlp.c_proj",
      "wg"
    ],
    "use_residual": false
  },
  "no_bias": true,
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "onnx_safe": null,
  "rotary_emb_base": 10000,
  "rotary_pct": 1.0,
  "scale_attn_weights": true,
  "seq_length": 8192,
  "softmax_in_fp32": false,
  "tie_word_embeddings": false,
  "tokenizer_class": "QWenTokenizer",
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.31.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_cache_kernel": false,
  "use_cache_quantization": false,
  "use_dynamic_ntk": true,
  "use_flash_attn": false,
  "use_logn_attn": true,
  "use_mm_proj": true,
  "video_global_proj": false,
  "video_projector_type": "linear",
  "video_spatial_proj": false,
  "video_temproal_proj": false,
  "vocab_size": 151936
}