{ "architectures": [ "Mistral4Model" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "first_k_dense_replace": 0, "head_dim": 128, "hidden_act": "gelu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 32, "kv_lora_rank": 256, "max_position_embeddings": 512, "model_type": "mistral4", "moe_intermediate_size": 16, "n_group": 1, "n_routed_experts": 128, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 2, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "pretraining_tp": 1, "q_lora_rank": 1024, "qk_head_dim": 128, "qk_nope_head_dim": 64, "qk_rope_head_dim": 64, "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": 512, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 8192, "partial_rotary_factor": 0.5, "rope_theta": 10000.0, "rope_type": "yarn", "type": "yarn" }, "routed_scaling_factor": 1.0, "tie_word_embeddings": false, "topk_group": 1, "transformers_version": "5.16.0.dev0", "use_cache": true, "v_head_dim": 128, "vocab_size": 99 }