# Finetune generative model
**URL:**
**Author:**  [@welu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fwelu)%5C
**Post date:** [March 2, 2023, 11:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-generative-model%2F32927%2F1 "2023-03-02T23:11:52Z")
I want to train a model on my custom documentation in a way it is able to answer related questions like chatgpt style (generative way). But I am lost. What is the best method to do this and what is the best model for the task.
---
**Author:**  [@gaganluthra](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgaganluthra)%5C
**Post date:** [March 7, 2023, 4:36pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-generative-model%2F32927%2F2 "2023-03-07T16:36:47Z")
I am a total beginner too. However, I will try my best.
I tried to solve a similar problem as you, and have tried a few things.
So far I am unable to make any opensource model work for this (or in general).
However, I saw somewhere in OpenAI API docs that you can upload documents and their models will answer questions from your documentation.
I have successly been able to use davinci model playground to answer questions based on the context (included in the prompt). In their playground there is a “chat” preset. I used that and modified it to my use case.
I havent deployed it anywhere yet, but as an experiment my mind was almost blown!
Because we both are working on a similar problem, I would like to stay updated on your progress too.
---
**Author:**  [@welu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fwelu)%5C
**Post date:** [March 9, 2023, 10:34pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-generative-model%2F32927%2F3 "2023-03-09T22:34:53Z")
Sure. I like the idea of keep updating each other.
For the moment I think this is the best approach I have found : [google/t5-11b-ssm-tqa · Hugging Face](https://huggingface.co/google/t5-11b-ssm-tqa?text=When+was+Franklin+D.+Roosevelt+born%3F)
Finetune this model would give us the QA model we need. But I need to dive deeper into the documentation.