koheiarailippo/toxicity_detection_labeled_OnlyGerman
04
1{2 "_sliding_window_pattern": 6,3 "architectures": [4 "Gemma3TextForSequenceClassification"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "attn_logit_softcapping": null,9 "bos_token_id": 2,10 "dtype": "bfloat16",11 "eos_token_id": 1,12 "final_logit_softcapping": null,13 "head_dim": 256,14 "hidden_activation": "gelu_pytorch_tanh",15 "hidden_size": 640,16 "initializer_range": 0.02,17 "intermediate_size": 2048,18 "layer_types": [19 "sliding_attention",20 "sliding_attention",21 "sliding_attention",22 "sliding_attention",23 "sliding_attention",24 "full_attention",25 "sliding_attention",26 "sliding_attention",27 "sliding_attention",28 "sliding_attention",29 "sliding_attention",30 "full_attention",31 "sliding_attention",32 "sliding_attention",33 "sliding_attention",34 "sliding_attention",35 "sliding_attention",36 "full_attention"37 ],38 "max_position_embeddings": 32768,39 "model_type": "gemma3_text",40 "num_attention_heads": 4,41 "num_hidden_layers": 18,42 "num_key_value_heads": 1,43 "pad_token_id": 0,44 "problem_type": "single_label_classification",45 "query_pre_attn_scalar": 256,46 "rms_norm_eps": 1e-06,47 "rope_parameters": {48 "full_attention": {49 "rope_theta": 1000000.0,50 "rope_type": "default"51 },52 "sliding_attention": {53 "rope_theta": 10000.0,54 "rope_type": "default"55 }56 },57 "sliding_window": 512,58 "tie_word_embeddings": true,59 "transformers_version": "5.0.0",60 "use_bidirectional_attention": false,61 "use_cache": false,62 "vocab_size": 26214463}64 