aieng-lab/starcoder2-7b_commit-intent

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  },19  "initializer_range": 0.018042,20  "intermediate_size": 18432,21  "label2id": {22    "LABEL_0": 0,23    "LABEL_1": 1,24    "LABEL_2": 225  },26  "layer_norm_epsilon": 1e-05,27  "max_position_embeddings": 16384,28  "mlp_type": "default",29  "model_type": "starcoder2",30  "norm_epsilon": 1e-05,31  "norm_type": "layer_norm",32  "num_attention_heads": 36,33  "num_hidden_layers": 32,34  "num_key_value_heads": 4,35  "pad_token_id": 0,36  "residual_dropout": 0.1,37  "rope_scaling": null,38  "rope_theta": 1000000,39  "scale_attention_softmax_in_fp32": true,40  "scale_attn_weights": true,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