{
  "_name_or_path": "fdschmidt93/NLLBLLM2Vec",
  "architectures": [
    "NLLBLLM2Vec"
  ],
  "auto_map": {
    "AutoConfig": "configuration_nllbllm2vec.NLLBLLM2VecConfig",
    "AutoModel": "modeling_nllbllm2vec.NLLBLLM2Vec",
    "AutoModelForSequenceClassification": "modeling_nllbllm2vec.NLLBLLM2VecForSequenceClassification"
  },
  "llm2vec_config": {
    "_name_or_path": "McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp",
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "model_type": "llama",
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 500000,
    "torch_dtype": "bfloat16",
    "use_cache": false,
    "vocab_size": 128256
  },
  "model_type": "nllb-llm2vec",
  "nllb_config": {
    "_name_or_path": "facebook/nllb-200-distilled-600M",
    "architectures": [
      "M2M100Encoder"
    ],
    "decoder_layerdrop": 0,
    "encoder_layerdrop": 0,
    "max_length": 200,
    "model_type": "m2m_100",
    "tokenizer_class": "NllbTokenizer",
    "torch_dtype": "bfloat16",
    "vocab_size": 256206
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2"
}