{
  "architectures": [
    "ClmModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "max_position_embeddings": 40960,
  "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": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "clm_hidden_size": 4096,
  "clm_width": 1536,
  "clm_depth": 3,
  "clm_projection_dim": 512,
  "clm_activation": "gelu",
  "clm_layernorm": true,
  "clm_residual": false,
  "clm_logit_scale": 4.613248825073242,
  "clm_provenance": {
    "checkpoint": "CLM_v0.1-8B.pt",
    "checkpoint_sha256": "b2b4a8c9c2d39263eff78a351eb909a342ce9b3bf21a3f07c1d1bf15f1c4eda5",
    "base_model": "Qwen/Qwen3-8B",
    "base_revision": "b968826d9c46dd6066d109eabc6255188de91218",
    "reference": "https://github.com/Contrastive-LM/CLM"
  }
}