| { | |
| "_sliding_window_pattern": 6, | |
| "architectures": [ | |
| "Gemma3TextForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 640, | |
| "id2label": { | |
| "0": "very positive", | |
| "1": "positive", | |
| "2": "somewhat positive", | |
| "3": "neutral", | |
| "4": "somewhat negative", | |
| "5": "negative", | |
| "6": "very negative" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "label2id": { | |
| "very positive": 0, | |
| "positive": 1, | |
| "somewhat positive": 2, | |
| "neutral": 3, | |
| "somewhat negative": 4, | |
| "negative": 5, | |
| "very negative": 6 | |
| }, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_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": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "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": "5.5.0", | |
| "use_bidirectional_attention": false, | |
| "use_cache": true, | |
| "vocab_size": 262144 | |
| } |