config.json

{
  "activation_backend": "silu",
  "architectures": [
    "HumanVForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "attn_backend": "gqa_matmul",
  "attn_implementation": "eager",
  "bos_token_id": 151643,
  "dtype": "float32",
  "eos_token_id": 151643,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_dropout": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "kv_cache_dtype": "auto",
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention"
  ],
  "max_position_embeddings": 2048,
  "max_window_layers": 0,
  "mlp_bias": false,
  "model_type": "humanv",
  "norm_backend": "rmsnorm",
  "num_attention_heads": 8,
  "num_hidden_layers": 12,
  "num_key_value_heads": 4,
  "pad_token_id": 151643,
  "resid_dropout": 0.1,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "rope_partial_rotary_factor": 1.0,
  "selective_rope_scale": 1.0,
  "sliding_window": null,
  "sparse_attention_impl": "local_global_block",
  "sparse_attention_window": 256,
  "sparse_block_size": 64,
  "sparse_global_block_stride": 4,
  "sparse_global_num_blocks": 2,
  "sparse_local_num_blocks": 4,
  "sparse_prefill_chunk_blocks": 16,
  "transformers_version": "5.0.0.dev0",
  "use_cache": false,
  "use_selective_rope": false,
  "use_sliding_window": false,
  "use_sparse_attention": true,
  "vocab_size": 151665
}