APudding/bigcode-starcoderbase-1b-finetuned-defect-detection

1{2  "_name_or_path": "bigcode/starcoderbase-1b",3  "activation_function": "gelu_pytorch_tanh",4  "architectures": [5    "GPTBigCodeForSequenceClassification"6  ],7  "attention_softmax_in_fp32": true,8  "attn_pdrop": 0.1,9  "bos_token_id": 0,10  "embd_pdrop": 0.1,11  "eos_token_id": 0,12  "finetuning_task": "text-classification",13  "inference_runner": 0,14  "initializer_range": 0.02,15  "layer_norm_epsilon": 1e-05,16  "max_batch_size": null,17  "max_sequence_length": null,18  "model_type": "gpt_bigcode",19  "multi_query": true,20  "n_embd": 2048,21  "n_head": 16,22  "n_inner": 8192,23  "n_layer": 24,24  "n_positions": 8192,25  "pad_key_length": true,26  "pad_token_id": 0,27  "pre_allocate_kv_cache": false,28  "problem_type": "single_label_classification",29  "resid_pdrop": 0.1,30  "scale_attention_softmax_in_fp32": true,31  "scale_attn_weights": true,32  "summary_activation": null,33  "summary_first_dropout": 0.1,34  "summary_proj_to_labels": true,35  "summary_type": "cls_index",36  "summary_use_proj": true,37  "torch_dtype": "float32",38  "transformers_version": "4.39.3",39  "use_cache": true,40  "validate_runner_input": true,41  "vocab_size": 4915242}43