config.json

{
  "transformers_version": "5.5.3",
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "bfloat16",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 151936,
  "hidden_size": 4096,
  "intermediate_size": 12288,
  "num_hidden_layers": 36,
  "num_attention_heads": 32,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "hidden_act": "silu",
  "max_position_embeddings": 40960,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "tie_word_embeddings": false,
  "rope_parameters": {
    "rope_theta": 1000000,
    "rope_type": "default"
  },
  "attention_bias": false,
  "use_sliding_window": false,
  "sliding_window": null,
  "max_window_layers": 36,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "attention_dropout": 0.0,
  "pad_token_id": null,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "_name_or_path": "Qwen/Qwen3-8B",
  "model_type": "qwen3",
  "output_attentions": false,
  "torch_dtype": "bfloat16"
}