{
  "_name_or_path": "memoryllm-7b",
  "add_bos_embedding": true,
  "add_pad_token": false,
  "add_positional_embedding": true,
  "architectures": [
    "MemoryLLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "delta_memory_ratio": 1.0,
  "drop_memory_token": false,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "interpolate_position_ids": true,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "memoryllm",
  "new_delta_memory_length": 8.0,
  "new_memory_embedding_fullset": true,
  "num_attention_heads": 32,
  "num_blocks": 30,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_tokens": 256,
  "pad_to_max_length": false,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "put_memory_on_cpu": false,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "share_position_ids": false,
  "shrink_to_one_embedding": true,
  "split_positional_embedding": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.40.0",
  "use_cache": true,
  "use_negative_position_ids": false,
  "vocab_size": 32000
}