config.json

{
  "architectures": [
    "SmallThinkerForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_smallthinker.SmallThinkerConfig",
    "AutoModel": "modeling_smallthinker.SmallThinkerForCausalLM",
    "AutoModelForCausalLM": "modeling_smallthinker.SmallThinkerForCausalLM"
  },
  "bos_token_id": 151643,
  "eos_token_id": [151643,151645],
  "head_dim": 128,
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "max_length": null,
  "max_position_embeddings": 32768,
  "model_name": "smallthinker_4b_instruct",
  "model_type": "smallthinker",
  "moe_ffn_hidden_size": 768,
  "moe_num_active_primary_experts": 4,
  "moe_num_primary_experts": 32,
  "norm_topk_prob": true,
  "num_attention_heads": 12,
  "num_hidden_layers": 32,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "repetition_penalty": null,
  "rms_norm_eps": 1e-06,
  "rope_layout": [
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1
  ],
  "rope_scaling": null,
  "rope_theta": 1.5e6,
  "sliding_window_size": 4096,
  "sliding_window_layout": [
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0
  ],
  "temperature": null,
  "tie_word_embeddings": true,
  "tokenizer_class": "Qwen2Tokenizer",
  "top_p": null,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.3",
  "use_cache": false,
  "vocab_size": 151936
}