llm-selector / config.json
JeffreyHuang's picture
Training in progress, epoch 1
e89aa3d
{
"_name_or_path": "distilbert-base-uncased",
"activation": "gelu",
"architectures": [
"DistilBertForSequenceClassification"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"id2label": {
"0": "gpt-3.5-turbo",
"1": "gpt-4",
"2": "azure_open_ai",
"3": "gpt-3.5-turbo-16k",
"4": "cohere",
"5": "vertexai",
"6": "bedrock_titan",
"7": "bedrock_grande",
"8": "bedrock_jumbo",
"9": "bedrock_claudie",
"10": "bedrock_claudie_instant"
},
"initializer_range": 0.02,
"label2id": {
"azure_open_ai": 2,
"bedrock_claudie": 9,
"bedrock_claudie_instant": 10,
"bedrock_grande": 7,
"bedrock_jumbo": 8,
"bedrock_titan": 6,
"cohere": 4,
"gpt-3.5-turbo": 0,
"gpt-3.5-turbo-16k": 3,
"gpt-4": 1,
"vertexai": 5
},
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"pad_token_id": 0,
"problem_type": "single_label_classification",
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"vocab_size": 30522
}