model_configs/qwen3_100M/config.json

{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "eos_token_id": 3,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 2048,
  "max_window_layers": 24,
  "model_type": "qwen3",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 2200
}