config.json

{
  "architectures": [
    "QuasarForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_qwen3_5.QuasarConfig",
    "AutoModelForCausalLM": "modeling_qwen3_5.QuasarForCausalLM"
  },
  "bos_token_id": null,
  "dtype": "bfloat16",
  "eos_token_id": null,
  "head_dim": 256,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 16,
  "linear_num_value_heads": 32,
  "linear_value_head_dim": 128,
  "max_position_embeddings": 32768,
  "model_type": "quasar_text",
  "num_attention_heads": 16,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "pad_token_id": null,
  "partial_rotary_factor": 0.25,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "partial_rotary_factor": 0.25,
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.7.0",
  "use_cache": true,
  "use_gla": false,
  "use_nope": false,
  "vocab_size": 248320
}