last-checkpoint/config.json

{
  "architectures": [
    "SmalLmForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "Azrail/smallm_70--config.SmalLmConfig",
    "AutoModelForCausalLM": "Azrail/smallm_70--model.SmalLmForCausalLM"
  },
  "balancing_coef": 0.0001,
  "bos_token_id": 1,
  "embedding_dropout": 0.0,
  "eos_token_id": 0,
  "expert_size": 576,
  "gate_noise": false,
  "head_size": 64,
  "hidden_size": 512,
  "high_rotations": 32,
  "initializer_range": 0.02,
  "intermediate_size": 1024,
  "layer_dropout": 0.1,
  "low_rotations": 1,
  "max_seq_len": 2048,
  "mlp_bias": false,
  "model_type": "smallm",
  "moe_bias": false,
  "moe_period": 2,
  "no_moe_layers": 10,
  "noisy_experts": false,
  "num_attention_heads": 8,
  "num_hidden_layers": 20,
  "num_kv_heads": 2,
  "original_seq_len": 1024,
  "pad_token_id": 0,
  "positional_bias_type": "rope",
  "rms_affine": false,
  "rms_norm_eps": 1e-06,
  "rope_base": 100000,
  "routed_experts": 8,
  "shared_experts": 1,
  "sliding_window_attention": true,
  "sliding_window_context": 1024,
  "sliding_window_period": 4,
  "static_residual": false,
  "token_experts": 3,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.50.3",
  "use_cache": true,
  "use_moe": false,
  "vocab_size": 60000
}