sft/hyperrouter/config.json

{
  "_name_or_path": "/cm/archive/namnv78/checkpoints/phi3mini-clip/pft",
  "architectures": [
    "LlavaPhiForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
  },
  "balance_loss_coef": 0.1,
  "bos_token_id": 1,
  "clip_smoe": true,
  "dropout": false,
  "embd_pdrop": 0.0,
  "eos_token_id": 32000,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "local_rank": 0,
  "max_position_embeddings": 4096,
  "mlp_smoe": true,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "moe",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "model_type": "llava_phi",
  "moe_name": "hyperrouter",
  "num_attention_heads": 32,
  "num_experts": 4,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_layers": 3,
  "num_selected": 2,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 32000,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "router_z_loss_coef": 0.01,
  "scales": [
    1,
    3
  ],
  "sliding_window": 2047,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "topk_max": 2,
  "topk_min": 1,
  "torch_dtype": "bfloat16",
  "training": true,
  "transformers_version": "4.43.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": false,
  "use_mm_proj": true,
  "vocab_size": 32064
}