{
  "_name_or_path": "llmware/slim-qwen-extract-500m",
  "aib_version": "model_archive_072424_qwen05_extract_eot_3",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 896,
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "max_position_embeddings": 131072,
  "max_window_layers": 24,
  "model_type": "qwen2",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": true,
  "trained": "custom training",
  "training_comments": "qwen2-500m-extract-eot-072424-3",
  "training_dataset": [
    "extract2_new_031724_eot_2_9442.jsonl"
  ],
  "training_timestamp": "Wed Jul 24 10:27:36 2024",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}