LLARA-passage-paddle/config.json

{
  "_name_or_path": "LLARA-passage",
  "alibi": false,
  "architectures": [
    "LlamaModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dpo_config": null,
  "dtype": "float16",
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "immediate_clear_past_key_value": false,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "long_sequence_init_args": {},
  "long_sequence_strategy_name": null,
  "long_sequence_strategy_type": null,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "paddlenlp_version": "3.0.0b4.post20251031",
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_scaling_factor": 1.0,
  "rope_scaling_type": null,
  "rope_theta": 10000.0,
  "seq_length": 2048,
  "tie_word_embeddings": false,
  "use_flash_attention_for_generation": false,
  "use_last_token_for_generation": false,
  "use_long_sequence_strategies": false,
  "vocab_size": 32016
}