config.json

{
  "architectures": [
    "Mistral4ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "float32",
  "eos_token_id": 2,
  "first_k_dense_replace": 1,
  "head_dim": 24,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 32,
  "kv_lora_rank": 16,
  "max_position_embeddings": 1048576,
  "model_type": "mistral4",
  "moe_intermediate_size": 16,
  "n_group": 2,
  "n_routed_experts": 4,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 4,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 3,
  "num_key_value_heads": 4,
  "pad_token_id": 11,
  "pretraining_tp": 1,
  "q_lora_rank": 32,
  "qk_head_dim": 24,
  "qk_nope_head_dim": 16,
  "qk_rope_head_dim": 8,
  "rms_norm_eps": 1e-06,
  "rope_interleave": true,
  "rope_parameters": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 128.0,
    "llama_4_scaling_beta": 0.1,
    "max_position_embeddings": 1048576,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 8192,
    "partial_rotary_factor": 0.3333333333333333,
    "rope_theta": 10000.0,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "routed_scaling_factor": 1.0,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "transformers_version": "5.3.0.dev0",
  "use_cache": true,
  "v_head_dim": 16,
  "vocab_size": 32000,
  "transformers.js_config": {
    "use_external_data_format": {
      "model.onnx": 1,
      "model_fp16.onnx": 1
    },
    "kv_cache_dtype": {
      "q4f16": "float16",
      "fp16": "float16"
    }
  }
}