config.json

{
  "architectures": [
    "KeeperModelForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_keeper.KeeperConfig",
    "AutoModel": "tokenizer_keeper.KeeperTokenizer",
    "AutoModelForCausalLM": "model_keeper.KeeperModelForCausalLM"
  },
  "device_map": "auto",
  "model_config": {
    "_name_or_path": "google/gemma-2b-it",
    "architectures": [
      "GemmaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 2,
    "eos_token_id": 1,
    "head_dim": 256,
    "hidden_act": "gelu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 16384,
    "max_position_embeddings": 8192,
    "model_type": "gemma",
    "num_attention_heads": 8,
    "num_hidden_layers": 18,
    "num_key_value_heads": 1,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.38.0.dev0",
    "use_cache": true,
    "vocab_size": 256000
  },
  "model_type": "keeper",
  "retriever_config": {
    "_name_or_path": "AdrienB134/ColBERTv1.0-bert-based-spanish-mmarcoES",
    "architectures": [
      "HF_ColBERT"
    ],
    "attention_probs_dropout_prob": 0.1,
    "classifier_dropout": null,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-12,
    "max_position_embeddings": 512,
    "model_type": "bert",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "output_past": true,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "torch_dtype": "float32",
    "transformers_version": "4.35.2",
    "type_vocab_size": 2,
    "use_cache": true,
    "vocab_size": 31002
  },
  "torch_dtype": "float32",
  "transformers_version": "4.39.2"
}