Hah that one is so weird… https://
huggingface.co/hkunlp/instruc
tor-xl
… "Represent the Wikipedia question for retrieving supporting documents:"
CODE
-
Instructor-XL Model Shows Unusual Wikipedia Question Retrieval Prompt
By
–
-
Keras with PyTorch matches vanilla PyTorch performance when compiled
By
–
That's because Keras + torch is not compiled by default whereas the native torch models are compiled. Keras+torch has the same performance as vanilla torch.
-
Building AI Software for Unstructured Data Processing
By
–
For some well specified tasks yes, but I'm trying to build software for inexperienced users who just want to dump in a bunch of raw input and get structured output back out again
-
Framework Comparison: JAX, PyTorch, TensorFlow Development Experience
By
–
I agree with your point that people hours are worth more than GPU hours (except for large-scale training runs or inference workloads of course…). Having been developing in all three frameworks (torch, TF, JAX) extensively over the past year, I've personally found JAX to be the
-
Keras torch backend performance overhead compilation optimization
By
–
Keras adds virtually no overhead over torch actually… the torch backend numbers are much worse simply because Keras + torch is not compiled by default, whereas the native torch models were compiled with the best compilation config we found. Keras + torch has essentially the
-
Exploring local AI alternatives to cloud API dependencies
By
–
Yeah I've been defaulting to those because they're convenient, but I want to explore the other options – especially the ones I can run locally if I want as insurance against the API shutting down someday
-
Cohere Embeddings Input Types for AI Applications
By
–
For Cohere embeddings it's input_type="search_document", "search_query", "classification", "clustering"
-
Adding Embedding Model Support to LLM CLI Tool
By
–
The reason I ask is I want to add support for this kind of model to my LLM CLI tool – https://
llm.datasette.io/en/stable/embe
ddings/index.html
… – and I'm trying to figure out the right terminology I've seen these called task types, input types and prefixes already. I'm considering "modes" as the LLM UI term -
Voyage AI Input Types for Embeddings Documentation
By
–
Thanks, yeah it looks like they call these "input types" https://
docs.voyageai.com/docs/embeddings -
RAG Implementation: Embedding Passages and Queries Separately
By
–
Being able to embed your content as "passage" but questions people ask about it as "query" is useful for implementing RAG – a user's question might not naturally embed to a similar location as content that answers that question, this trick helps fix that