Sentence Similarity
sentence-transformers
PyTorch
Transformers
English
t5
text-embedding
embeddings
information-retrieval
beir
text-classification
language-model
text-clustering
text-semantic-similarity
text-evaluation
prompt-retrieval
text-reranking
feature-extraction
English
Sentence Similarity
natural_questions
ms_marco
fever
hotpot_qa
mteb
Eval Results (legacy)
Any guidelines on composing instructions?
#8
by hiranya911 - opened
Do you have insights or best practices around crafting instructions for embeddings? As I understand, an instruction has the following general format:
Represent the domain text_type for task_objective:
What are the values we can specify for text_type and task_objective? Can we specify anything or is there a limited number of supported values?
Hi, Thanks a lot for your interest in the INSTRUCTOR model!
We provide a few examples in Table 5 of our paper (https://arxiv.org/pdf/2212.09741.pdf), but the values of the domain, text type, and task objective often depend on the specific task and are not restricted to the values mentioned in Table 5.
Feel free to add any further questions or comments!