checkpoint-10000/config.json

{
  "_name_or_path": "RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "eos_token_id": 147075,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 32768,
  "max_window_layers": 36,
  "model_type": "qwen2",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 2,
  "pad_token_id": 147075,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 147097
}