model_config.json

{
  "model_name": "hf_model",
  "architecture": "lfm2",
  "hidden_size": 1024,
  "num_hidden_layers": 16,
  "num_attention_heads": 16,
  "num_key_value_heads": 8,
  "head_dim": 64,
  "vocab_size": 65536,
  "context_length": 2048,
  "rms_norm_eps": 1e-05,
  "bos_token_id": 1,
  "eos_token_id": 7,
  "quantization": "int4",
  "compute_units": "ALL",
  "parts": {
    "model": "model.mlpackage"
  },
  "tokenizer_repo": "hf_model",
  "lfm2_conv_l_pad": 3
}