{ "architectures": [ "SquaredReLUQwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoModelForCausalLM": "patch.SquaredReLUQwen3ForCausalLM" }, "bos_token_id": 50030, "dtype": "bfloat16", "eos_token_id": 50031, "head_dim": 64, "hidden_act": "squared_relu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 2816, "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", "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": 8192, "max_window_layers": 28, "model_name": "qwen3_from_scratch", "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 50, "num_key_value_heads": 4, "pad_token_id": 50034, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "5.5.0", "unsloth_version": "2026.5.2", "use_cache": false, "use_sliding_window": false, "vocab_size": 50048 }