config.json

{
  "d_model": 768,
  "n_layer": 24,
  "vocab_size": 4000,
  "d_conv": 4,
  "expand": 2,
  "d_state": 64,
  "head_dim": 64,
  "d_inner": 1536,
  "n_heads": 24,
  "rms_norm_eps": 1e-05,
  "pad_vocab_size_multiple": 16,
  "tie_word_embeddings": true,
  "model_type": "mamba2",
  "architectures": [
    "Mamba2ForCausalLM"
  ],
  "torch_dtype": "float16",
  "transformers_version": "4.40.0"
}