llama3-chatqa

121.7K 1 year ago

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

8b 70b

Models

View all →

35 models

llama3-chatqa:latest

4.7GB · 8K context window · Text · 1 year ago

llama3-chatqa:8b

latest

4.7GB · 8K context window · Text · 1 year ago

llama3-chatqa:70b

40GB · 8K context window · Text · 1 year ago

Readme

ChatQA-1.5 is built on top of the Llama-3 base model, and incorporates conversational QA data to enhance its tabular and arithmetic calculation capability.

ChatQA-1.5 has two variants:

  • Llama3-ChatQA-1.5-8B llama3-chatqa:8b
  • Llama3-ChatQA-1.5-70B llama3-chatqa:70b

References

Website

Hugging Face