config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "Qwen2ForSequenceClassification" |
| 4 | ], |
| 5 | "attention_dropout": 0.0, |
| 6 | "bos_token_id": 151643, |
| 7 | "dtype": "bfloat16", |
| 8 | "eos_token_id": 151645, |
| 9 | "hidden_act": "silu", |
| 10 | "hidden_size": 16, |
| 11 | "id2label": { |
| 12 | "0": "LABEL_0" |
| 13 | }, |
| 14 | "initializer_range": 0.02, |
| 15 | "intermediate_size": 32, |
| 16 | "label2id": { |
| 17 | "LABEL_0": 0 |
| 18 | }, |
| 19 | "layer_types": [ |
| 20 | "full_attention", |
| 21 | "full_attention" |
| 22 | ], |
| 23 | "max_position_embeddings": 32768, |
| 24 | "max_window_layers": 70, |
| 25 | "model_type": "qwen2", |
| 26 | "num_attention_heads": 4, |
| 27 | "num_hidden_layers": 2, |
| 28 | "num_key_value_heads": 2, |
| 29 | "rms_norm_eps": 1e-06, |
| 30 | "rope_scaling": null, |
| 31 | "rope_theta": 1000000.0, |
| 32 | "sliding_window": null, |
| 33 | "tie_word_embeddings": false, |
| 34 | "transformers_version": "4.57.3", |
| 35 | "use_cache": true, |
| 36 | "use_sliding_window": false, |
| 37 | "vocab_size": 152064 |
| 38 | } |
| 39 | |