home.social

#semanticfinder — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #semanticfinder, aggregated by home.social.

  1. Dominik Weckmüller @DomeGIS ·

    Just added the current leader /UAE-Large-V1 to and it's performing great! Would love a base or small version to have it slightly faster for in-browser semantic search.
    Test here: do-me.github.io/SemanticFinder/

    #mteb #whereisai #semanticfinder
  2. Dominik Weckmüller @[email protected] ·

    ✨ Open source RAG (Retrieval Augmented Generation) right in your browser! ✨

    #SemanticFinder now offers an 𝐚𝐝𝐯𝐚𝐧𝐜𝐞𝐝 𝐜𝐡𝐚𝐭 & 𝐬𝐮𝐦𝐦𝐚𝐫𝐲 𝐟𝐞𝐚𝐭𝐮𝐫𝐞 for your search results - all in your browser.

    💡There are very few capable small LLMs that offer high-quality results. Quantized LaMini-Flan-T5-783M offers good performance with 3-4s load time and >6 tokens/s after model download on an old i7.

    do-me.github.io/SemanticFinder

    #transformers #RAG #AI #LLM #embeddings #semanticsearch #text2text #Flan #T5

    #semanticfinder #transformers #rag #ai #llm #embeddings
  3. Dominik Weckmüller @DomeGIS ·

    ✨ Open source RAG (Retrieval Augmented Generation) right in your browser! ✨

    now offers an 𝐚𝐝𝐯𝐚𝐧𝐜𝐞𝐝 𝐜𝐡𝐚𝐭 & 𝐬𝐮𝐦𝐦𝐚𝐫𝐲 𝐟𝐞𝐚𝐭𝐮𝐫𝐞 for your search results - all in your browser.

    💡There are very few capable small LLMs that offer high-quality results. Quantized LaMini-Flan-T5-783M offers good performance with 3-4s load time and >6 tokens/s after model download on an old i7.

    do-me.github.io/SemanticFinder/

    #semanticfinder #transformers #rag #ai #llm #embeddings
  4. Dominik Weckmüller @[email protected] ·

    ✨ Open source RAG (Retrieval Augmented Generation) right in your browser! ✨

    #SemanticFinder now offers an 𝐚𝐝𝐯𝐚𝐧𝐜𝐞𝐝 𝐜𝐡𝐚𝐭 & 𝐬𝐮𝐦𝐦𝐚𝐫𝐲 𝐟𝐞𝐚𝐭𝐮𝐫𝐞 for your search results - all in your browser.

    💡There are very few capable small LLMs that offer high-quality results. Quantized LaMini-Flan-T5-783M offers good performance with 3-4s load time and >6 tokens/s after model download on an old i7.

    do-me.github.io/SemanticFinder

    #transformers #RAG #AI #LLM #embeddings #semanticsearch #text2text #Flan #T5

    #semanticfinder #transformers #rag #ai #llm #embeddings
  5. Dominik Weckmüller @[email protected] ·

    ✨ Open source RAG (Retrieval Augmented Generation) right in your browser! ✨

    #SemanticFinder now offers an 𝐚𝐝𝐯𝐚𝐧𝐜𝐞𝐝 𝐜𝐡𝐚𝐭 & 𝐬𝐮𝐦𝐦𝐚𝐫𝐲 𝐟𝐞𝐚𝐭𝐮𝐫𝐞 for your search results - all in your browser.

    💡There are very few capable small LLMs that offer high-quality results. Quantized LaMini-Flan-T5-783M offers good performance with 3-4s load time and >6 tokens/s after model download on an old i7.

    do-me.github.io/SemanticFinder

    #transformers #RAG #AI #LLM #embeddings #semanticsearch #text2text #Flan #T5

    #t5 #flan #text2text #semanticsearch #embeddings #llm