config.json

{
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
"architectures": [
"LlamaEncoderModel"
],
"attention_bias": false,
"attention_dropout": 0,
"auto_map": {
  "AutoModel": "McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp--modeling_llama_encoder.LlamaEncoderModel"
},
"bos_token_id": 128000,
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 0.00001,
"rope_scaling": null,
"rope_theta": 500000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0.dev0",
"use_cache": true,
"vocab_size": 128256
}