{ "_sliding_window_pattern": 6, "architectures": [ "Gemma3Intent8LStudent" ], "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": null, "bos_token_id": 2, "classifier_dropout": 0.1, "dtype": "float32", "eos_token_id": 1, "final_logit_softcapping": null, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 320, "id2label": { "0": "provide_info", "1": "affirm", "2": "deny", "3": "correction", "4": "question", "5": "clarify_request", "6": "unclear" }, "initializer_range": 0.02, "intermediate_size": 1216, "keys_to_ignore_at_inference": [ "past_key_values", "pooled" ], "label2id": { "affirm": 1, "clarify_request": 5, "correction": 3, "deny": 2, "provide_info": 0, "question": 4, "unclear": 6 }, "layer_types": [ "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 32768, "model_type": "gemma3_text", "num_attention_heads": 4, "num_hidden_layers": 8, "num_key_value_heads": 1, "num_labels_intent": 7, "pad_token_id": 0, "pooling": "mean", "problem_type": "single_label_classification", "query_pre_attn_scalar": 256, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "rope_theta": 1000000.0, "rope_type": "default" }, "sliding_attention": { "rope_theta": 10000.0, "rope_type": "default" } }, "sliding_window": 512, "tie_word_embeddings": true, "transformers_version": "5.10.1", "use_bidirectional_attention": false, "use_cache": false, "vocab_size": 262144 }