{ "base_model_name": "Qwen/Qwen3-30B-A3B-Instruct-2507", "classifier_model_path": "/root/sandbagging-organism/data/classifier_model", "base_config": { "vocab_size": 151936, "max_position_embeddings": 262144, "hidden_size": 2048, "intermediate_size": 6144, "num_hidden_layers": 48, "num_attention_heads": 32, "use_sliding_window": false, "sliding_window": null, "num_key_value_heads": 4, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "attention_bias": false, "attention_dropout": 0.0, "rope_parameters": { "rope_theta": 10000000, "rope_type": "default" }, "decoder_sparse_step": 1, "moe_intermediate_size": 768, "num_experts_per_tok": 8, "num_local_experts": 128, "norm_topk_prob": true, "output_router_logits": false, "router_aux_loss_coef": 0.001, "mlp_only_layers": [], "pad_token_id": null, "bos_token_id": 151643, "eos_token_id": 151645, "tie_word_embeddings": false, "return_dict": true, "output_hidden_states": false, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "architectures": [ "Qwen3MoeForCausalLM" ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "_name_or_path": "Qwen/Qwen3-30B-A3B-Instruct-2507", "transformers_version": "5.3.0", "head_dim": 128, "max_window_layers": 48, "model_type": "qwen3_moe", "output_attentions": false }, "n_password_tokens": 17, "n_backdoor_tokens": 11, "password_steepness": 10.0, "gate_steepness": 100.0, "rope_parameters": { "rope_theta": 10000000, "rope_type": "default" }, "return_dict": true, "output_hidden_states": false, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "architectures": [ "SandbaggingSeparateForCausalLM" ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "_name_or_path": "", "transformers_version": "5.3.0", "vocab_size": 151936, "model_type": "sandbagging_separate", "output_attentions": false, "auto_map": { "AutoConfig": "modeling_sandbagging.SandbaggingSeparateConfig", "AutoModelForCausalLM": "modeling_sandbagging.SandbaggingSeparateForCausalLM" }, "classifier_config": { "vocab_size": 151936, "max_position_embeddings": 40960, "hidden_size": 1024, "intermediate_size": 3072, "num_hidden_layers": 28, "num_attention_heads": 16, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "attention_bias": false, "attention_dropout": 0.0, "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" ], "pad_token_id": null, "bos_token_id": 151643, "eos_token_id": 151645, "tie_word_embeddings": true, "rope_parameters": { "rope_theta": 1000000, "rope_type": "default" }, "return_dict": true, "output_hidden_states": false, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "architectures": [ "Qwen3ForCausalLM" ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "_name_or_path": "data/classifier_model", "transformers_version": "5.3.0", "model_type": "qwen3", "output_attentions": false } }