{ "architectures": [ "Ministral3Model" ], "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "bfloat16", "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "is_causal": false, "llama_4_scaling": { "beta": 0.1, "original_max_position_embeddings": 16384 }, "max_position_embeddings": 262144, "model_type": "ministral3", "nemo_version": "0.3.0rc0", "num_attention_heads": 24, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 11, "pooling": "avg", "rms_norm_eps": 1e-05, "rope_parameters": { "apply_yarn_scaling": false, "beta_fast": 32.0, "beta_slow": 1.0, "factor": 16.0, "llama_4_scaling_beta": 0.1, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 16384, "rope_theta": 1000000.0, "rope_type": "yarn", "type": "yarn" }, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "5.13.0", "use_cache": false, "vocab_size": 131072 }