Closed cgpeter96 closed 10 months ago
We have integrated the prompt within our code. If you want to use our scorers, you only need to give your query sentence for scoring complexity or query + response for scoring quality.
Our code will convert your input (i.e. query or query + response) to our designed format for scorers to score samples.
Hi @VPeterV. Related question: In the Score-First, Diversity-Aware Data Selection algorithm are the llama-13b sentence embeddings a mean of the token embeddings, the last token embedding, or something else?
Hi @VPeterV. Related question: In the Score-First, Diversity-Aware Data Selection algorithm are the llama-13b sentence embeddings a mean of the token embeddings, the last token embedding, or something else?
Hi @edbeeching ! We encode the sentence by using the hidden states of the last token for one sentence (i.e. the last token in query + response)
Only prompt? or prompt+response?