config.json

{
  "architectures": ["MambaSwarmForCausalLM"],
  "auto_map": {
    "AutoConfig": "configuration_mamba_swarm.MambaSwarmConfig",
    "AutoModelForCausalLM": "modeling_mamba_swarm.MambaSwarmForCausalLM"
  },
  "model_type": "mamba_swarm",
  "num_mamba_encoders": 5,
  "max_mamba_encoders": 1000,
  "d_model": 768,
  "d_state": 16,
  "d_conv": 4,
  "expand_factor": 2,
  "vocab_size": 50257,
  "max_sequence_length": 2048,
  "pad_token_id": 50256,
  "bos_token_id": 50256,
  "eos_token_id": 50256,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.36.0",
  "use_cache": true,
  "gating_config": {
    "gating_type": "learned",
    "top_k": 2,
    "load_balancing_loss_coef": 0.01
  },
  "routing_config": {
    "routing_strategy": "dynamic",
    "aggregation_method": "weighted_average"
  }
}