config.json

{
  "transformers_version": "5.5.0",
  "architectures": [
    "OutlierMoE"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "float32",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 152064,
  "hidden_size": 3584,
  "intermediate_size": 18944,
  "num_hidden_layers": 28,
  "num_attention_heads": 28,
  "num_key_value_heads": 4,
  "hidden_act": "silu",
  "max_position_embeddings": 32768,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "tie_word_embeddings": false,
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "use_sliding_window": false,
  "sliding_window": null,
  "max_window_layers": 28,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "attention_dropout": 0.0,
  "pad_token_id": null,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "_name_or_path": "/dev/shm/qwen7b",
  "model_type": "outlier_moe",
  "output_attentions": false,
  "n_experts": 8,
  "top_k": 2,
  "base_model": "Qwen/Qwen2.5-7B-Instruct"
}