| { |
| "architectures": [ |
| "RobertaForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "auto_map": { |
| "AutoModel": "modeling_roberta.RobertaModel", |
| "AutoModelForSequenceClassification": "modeling_roberta.RobertaForSequenceClassification" |
| }, |
| "bos_token_id": 126080, |
| "classifier_dropout": null, |
| "distillation_objective": "supervised_toxicity_with_teacher_kl", |
| "eos_token_id": 126081, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "neutral", |
| "1": "toxic" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "neutral": 0, |
| "toxic": 1 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 514, |
| "model_type": "roberta", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 126081, |
| "position_embedding_type": "absolute", |
| "position_pad_token_id": 1, |
| "prepend_cls_token": true, |
| "problem_type": "single_label_classification", |
| "student_cls_token_id": 126082, |
| "student_tokenizer_name": "GSAI-ML/LLaDA-8B-Base", |
| "teacher_embedding_init": { |
| "fallback": 0, |
| "initialized": 126346, |
| "skipped_hidden_size_mismatch": 0 |
| }, |
| "teacher_model_name": "s-nlp/roberta_toxicity_classifier", |
| "teacher_weight_init": { |
| "copied": 200, |
| "skipped": 1 |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.46.3", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 126346 |
| } |
|
|
