Nice to see an open weights model showing up this high on the Arena leaderboard Worth noting that Command R is licensed Creative Commons Non-Commercial, so it's great for research but not a dependable backup against API shutdown for commercial purposes
@simonw
-
textract-cli: Simple Raw Text Extraction Without Table Processing
By
–
textract-cli currently does the simplest possible thing: it dumps out just the raw text, making no effort to decipher tables
-
Building AI Software for Non-Expert Users
By
–
I've been experimenting with that too, but I'm mainly trying to build software for non-expert users here
-
Data Journalism Use Cases: Structured Extraction and Content Translation
By
–
In data journalism the use-cases are mainly around structured data extraction and other forms of transformation Inputting a 5MB HTML file to output a ~3MB CSV or JSON file for example Also things like "translate this report from Spanish to English" where the report might be >4k
-
Instructor-XL Model Shows Unusual Wikipedia Question Retrieval Prompt
By
–
Hah that one is so weird… https://
huggingface.co/hkunlp/instruc
tor-xl
… "Represent the Wikipedia question for retrieving supporting documents:" -
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
-
GPT-4 Turbo Output Limitations Explained
By
–
That's input though – the docs say output for gpt-4-turbo is limited to 4096
-
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