alfred

A robust conversational model designed to be used for both chat and instruct use cases.

40b
Hızlı Kurulum (Ollama kuruluysa)
ollama run alfred

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

EtiketBoyutBağlamGirdiKomut
latest 24GB 2K Text ollama run alfred:latest
40b 24GB 2K Text ollama run alfred:40b
40b-1023-q4_0 24GB 2K Text ollama run alfred:40b-1023-q4_0
40b-1023-q4_1 26GB 2K Text ollama run alfred:40b-1023-q4_1
40b-1023-q5_0 29GB 2K Text ollama run alfred:40b-1023-q5_0
40b-1023-q5_1 32GB 2K Text ollama run alfred:40b-1023-q5_1
40b-1023-q8_0 44GB 2K Text ollama run alfred:40b-1023-q8_0

Model Detayları ve Benchmarklar (kaynak: ollama.com)

Alfred is a robust conversational model created by LightOn, based on the Falcon 40B model. It’s designed to be used for both chat and instruct use cases.

Some of its features include:

  • Reduced Hallucinations: ability to minimize hallucinations, ensuring more accurate and reliable outputs.
  • Enhanced Self-Awareness: In situations where the model lacks a definitive answer, Alfred-40B-1023 is now programmed to state, “I don’t know”, enhancing its transparency and trustworthiness.
  • Superior ‘Chat with Docs’ Capability: Alfred-40B-1023 is trained to perform ‘Chat with Docs’ tasks like no other, streamlining document interaction and information retrieval.
  • Expanded Context: With an increased context of 8K tokens, Alfred-40B-1023 can comprehend and generate longer and more intricate content, ensuring detailed and comprehensive responses.

References

HuggingFace

Blog Post