config.json

{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "max_position_embeddings": 262144,
  "max_window_layers": 36,
  "model_type": "qwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "merge_info": {
    "run_id": "20250808_233922",
    "task": "unknown",
    "benchmark_scores": {
      "gpqa": 0.45454545454545453,
      "mmlu": 0.7251103831363054
    },
    "source_models": [
      "Qwen/Qwen3-4B-Instruct-2507",
      "Qwen/Qwen3-4B-Instruct-2507-FP8",
      "unsloth/Qwen3-4B-Instruct-2507",
      "huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated",
      "g-assismoraes/Qwen3-4B-Instruct-2507-imdb",
      "g-assismoraes/Qwen3-4B-Instruct-2507-assin2",
      "g-assismoraes/Qwen3-4B-Instruct-2507-faquad",
      "g-assismoraes/Qwen3-4B-Instruct-2507-hatebr",
      "g-assismoraes/Qwen3-4B-Instruct-2507-agnews",
      "BRlkl/BingoGuard-qwen3-4B-pt"
    ],
    "layer_configuration": []
  }
}