max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/config.json

{
  "_name_or_path": "Qwen/Qwen1.5-1.8B",
  "architectures": [
    "Qwen2ForSequenceClassification"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "finetuning_task": "text-classification",
  "hidden_act": "silu",
  "hidden_size": 2048,
  "id2label": {
    "0": "0",
    "1": "1",
    "2": "10",
    "3": "11",
    "4": "12",
    "5": "2",
    "6": "3",
    "7": "4",
    "8": "5",
    "9": "6",
    "10": "7",
    "11": "8",
    "12": "9"
  },
  "initializer_range": 0.02,
  "intermediate_size": 5504,
  "label2id": {
    "0": 0,
    "1": 1,
    "10": 2,
    "11": 3,
    "12": 4,
    "2": 5,
    "3": 6,
    "4": 7,
    "5": 8,
    "6": 9,
    "7": 10,
    "8": 11,
    "9": 12
  },
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_key_value_heads": 16,
  "pad_token_id": 151643,
  "problem_type": "single_label_classification",
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.0.dev0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151646
}