models/Jamba/config.json

{
  "architectures": [
    "JambaForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attn_layer_offset": 4,
  "attn_layer_period": 8,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "expert_layer_offset": 1,
  "expert_layer_period": 2,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 24576,
  "mamba_conv_bias": true,
  "mamba_d_conv": 4,
  "mamba_d_state": 16,
  "mamba_dt_rank": 512,
  "mamba_expand": 2,
  "mamba_proj_bias": false,
  "max_position_embeddings": 262144,
  "model_type": "jamba",
  "num_attention_heads": 64,
  "num_experts": 16,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 72,
  "num_key_value_heads": 8,
  "num_logits_to_keep": 1,
  "output_router_logits": false,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_mamba_kernels": true,
  "vocab_size": 65536
}