config.json

{
  "_name_or_path": "/nas-wulanchabu/shenweizhou.swz/models/qwen/Qwen2-7B",
  "architectures": [
    "Qwen2ForCausalLMandBIO"
  ],
  "attention_dropout": 0.0,
  "bi_label_type": "BIOE",
  "bi_loss_type": "ce",
  "bi_loss_weight": [
    10.0,
    10.0,
    1.0,
    10.0
  ],
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "id2label": {
    "0": "0",
    "1": "1"
  },
  "ignore_lm_head": false,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "label2id": {
    "0": 0,
    "1": 1
  },
  "label_smoothing": null,
  "lm_head_weight": {
    "66990": 0.5
  },
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}