| { |
| "architectures": [ |
| "SwePrunerVllmForTokenClassification" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 896, |
| "initializer_range": 0.02, |
| "intermediate_size": 4864, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 17, |
| "model_type": "qwen2", |
| "num_attention_heads": 14, |
| "num_hidden_layers": 17, |
| "num_key_value_heads": 2, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 1000000.0, |
| "sliding_window": 32768, |
| "tie_word_embeddings": true, |
| "torch_dtype": "float16", |
| "transformers_version": "4.43.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936, |
| "num_labels": 3, |
| "problem_type": "regression", |
| "io_processor_plugin": "swe_pruner", |
| "swe_pruner": { |
| "bottleneck": 128, |
| "dropout": 0.1, |
| "num_fusion_layers": 1, |
| "num_heads": 16, |
| "last_layer_expansion_size": 2432, |
| "last_layer_adapter_type": "gated", |
| "last_layer_activation": "polynorm", |
| "backbone_stop_layer": 17, |
| "pruned_attention_layers": [ |
| 6, |
| 16, |
| 17 |
| ], |
| "attention_type": "full", |
| "input_format": "plain_pruner", |
| "lora_merged": true, |
| "output_columns": [ |
| "prune_emission", |
| "keep_emission", |
| "document_log_probability" |
| ] |
| } |
| } |
|
|
