Team Ai
Modelpublic

aieng-lab/starcoder2-7b_comment-type-python

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes13downloads
config.json53 linesDownload Raw Back to root
1{2  "_name_or_path": "bigcode/starcoder2-7b",3  "activation_function": "gelu",4  "architectures": [5    "Starcoder2ForSequenceClassification"6  ],7  "attention_dropout": 0.1,8  "attention_softmax_in_fp32": true,9  "bos_token_id": 0,10  "embedding_dropout": 0.1,11  "eos_token_id": 0,12  "hidden_act": "gelu_pytorch_tanh",13  "hidden_size": 4608,14  "id2label": {15    "0": "LABEL_0",16    "1": "LABEL_1",17    "2": "LABEL_2",18    "3": "LABEL_3",19    "4": "LABEL_4"20  },21  "initializer_range": 0.018042,22  "intermediate_size": 18432,23  "label2id": {24    "LABEL_0": 0,25    "LABEL_1": 1,26    "LABEL_2": 2,27    "LABEL_3": 3,28    "LABEL_4": 429  },30  "layer_norm_epsilon": 1e-05,31  "max_position_embeddings": 16384,32  "mlp_type": "default",33  "model_type": "starcoder2",34  "norm_epsilon": 1e-05,35  "norm_type": "layer_norm",36  "num_attention_heads": 36,37  "num_hidden_layers": 32,38  "num_key_value_heads": 4,39  "pad_token_id": 0,40  "problem_type": "multi_label_classification",41  "residual_dropout": 0.1,42  "rope_scaling": null,43  "rope_theta": 1000000,44  "scale_attention_softmax_in_fp32": true,45  "scale_attn_weights": true,46  "sliding_window": 4096,47  "torch_dtype": "bfloat16",48  "transformers_version": "4.48.3",49  "use_bias": true,50  "use_cache": true,51  "vocab_size": 4915252}53