Nvidia Just Published ChatQA 1.5, a Llama3 QA/RAG Finetune

Re:Nvidia Just Published ChatQA 1.5, a Llama3 QA/RAG Finetune by noiseinvacuum on Thursday May 02, 2024 @02:01PM (#40239370)

Looks quite a solid fine tune from benchmark results. I iwsh they had added benchmark comparison to GPT 4 Turbo as well.

From the huggingface page:

Model Details

We introduce Llama3-ChatQA-1.5, which excels at conversational question answering (QA) and retrieval-augumented generation (RAG). Llama3-ChatQA-1.5 is built using the training recipe from ChatQA (1.0), and it is built on top of Llama-3 base model. Additionally, we incorporate more conversational QA data to enhance its tabular and arithmatic calculation capability. Llama3-ChatQA-1.5 has two variants: Llama3-ChatQA-1.5-8B and Llama3-ChatQA-1.5-70B. Both models were originally trained using Megatron-LM, we converted the checkpoints to Hugging Face format. Other Resources

[ Parent | on HN ]

Re:Nvidia Just Published ChatQA 1.5, a Llama3 QA/RAG Finetune by jaggs on Thursday May 02, 2024 @03:44PM (#40240617)

Any chance of getting this in a .gguf format?

[ Parent | on HN ]

Re:Nvidia Just Published ChatQA 1.5, a Llama3 QA/RAG Finetune by sp332 on Thursday May 02, 2024 @07:27PM (#40242466)

https://huggingface.co/models?search=Llama3-ChatQA-1.5%20ggu...

Bartowski and neopolita have the most options. DuckyBlender's repo is currently empty.

[ Parent | on HN ]

Re:Nvidia Just Published ChatQA 1.5, a Llama3 QA/RAG Finetune by jaggs on Friday May 03, 2024 @05:46AM (#40245838)

Thanks very much, that's great.

[ Parent | on HN ]