aieng-lab/starcoder2-3b_comment-type-python

1{2  "_name_or_path": "bigcode/starcoder2-3b",3  "architectures": [4    "Starcoder2ForSequenceClassification"5  ],6  "attention_dropout": 0.1,7  "bos_token_id": 0,8  "embedding_dropout": 0.1,9  "eos_token_id": 0,10  "hidden_act": "gelu_pytorch_tanh",11  "hidden_size": 3072,12  "id2label": {13    "0": "LABEL_0",14    "1": "LABEL_1",15    "2": "LABEL_2",16    "3": "LABEL_3",17    "4": "LABEL_4"18  },19  "initializer_range": 0.018042,20  "intermediate_size": 12288,21  "label2id": {22    "LABEL_0": 0,23    "LABEL_1": 1,24    "LABEL_2": 2,25    "LABEL_3": 3,26    "LABEL_4": 427  },28  "max_position_embeddings": 16384,29  "mlp_type": "default",30  "model_type": "starcoder2",31  "norm_epsilon": 1e-05,32  "norm_type": "layer_norm",33  "num_attention_heads": 24,34  "num_hidden_layers": 30,35  "num_key_value_heads": 2,36  "pad_token_id": 0,37  "problem_type": "multi_label_classification",38  "residual_dropout": 0.1,39  "rope_scaling": null,40  "rope_theta": 999999.4420358813,41  "sliding_window": 4096,42  "torch_dtype": "bfloat16",43  "transformers_version": "4.48.3",44  "use_bias": true,45  "use_cache": true,46  "vocab_size": 4915247}48