config.json

{
  "architectures": [
    "SmolLM3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": null,
  "eos_token_id": 128012,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 65536,
  "max_window_layers": 28,
  "mlp_bias": false,
  "model_type": "smollm3",
  "no_rope_layer_interval": 4,
  "no_rope_layers": [
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0
  ],
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 4,
  "pad_token_id": 128004,
  "pretraining_tp": 2,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "embed_tokens",
      "embedding",
      "lm_head",
      "multi_modal_projector",
      "merger",
      "modality_projection"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000.0,
  "sliding_window": null,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.1",
  "unsloth_fixed": true,
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 128256
}