final_model/config.json

{
  "max_length": 2048,
  "max_species_prefix": 0,
  "max_protein_prefix": 1024,
  "hidden_size": 750,
  "num_hidden_layers": 20,
  "num_attention_heads": 15,
  "mlp_ratio": 3.2,
  "prepend_species": true,
  "prepend_protein": true,
  "species_embedding_dim": 1024,
  "esm_model_name": "esmc_300m",
  "esm_device": "cuda:0",
  "esm_dtype": "bf16",
  "attn_impl": "mha",
  "num_kv_groups": 5
}