Hi, what is the difference between these two models? One (sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net) is used in the code, the other (sentence-t5-base-nlpl-code_search_net) is listed in the readme, but doesn't appear to be used.
In the code:
|
parser.add_argument('-m', '--model-name-or-path', metavar='MODEL', default='krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net', |
In the readme:
|
The application uses [sentence transformer](https://www.sbert.net/) model architecture to produce 'sentence' embeddings for functions and queries. The particular model is [krlvi/sentence-t5-base-nlpl-code_search_net](https://huggingface.co/krlvi/sentence-t5-base-nlpl-code_search_net) which is based of a [SentenceT5-Base](https://github.com/google-research/t5x_retrieval#released-model-checkpoints) checkpoint with 110M parameters and a pooling layer. |
Hi, what is the difference between these two models? One (sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net) is used in the code, the other (sentence-t5-base-nlpl-code_search_net) is listed in the readme, but doesn't appear to be used.
In the code:
semantic-code-search/src/semantic_code_search/cli.py
Line 51 in 6434ef7
In the readme:
semantic-code-search/README.md
Line 182 in 6434ef7