Closed ehartford closed 1 year ago
Thanks! I'll try it later
@johnsmith0031 Thank you. May I ask if it's possible to train a multi round conversation by directly adjusting to the following data format, “# GPT4All-like Data class TrainGPT4All(ATrainData): ... newline_ tokens = self.tokenizer("\n", return_tensors="pt")["input_ids"][0, 1:]”, Is it possible to fine tune a good conversation with a line break? However, the conversation length is indeed relatively short. I briefly tried truncating it to a maximum of 700, which slows down the training speed. By fine-tuning it on the existing Q&A Lora, a simple two round conversation is still possible. Moreover, the greedy algorithm used for reasoning may not seem as good as Q&A, but it may not be well trained, At that time, I tried to see if I could run through multiple rounds of conversations with data such as' {"topic": "Identify the OD one out. '" "input":' The conversation between human and AI assistant. ' n [| Human |] Identify the OD one out. n Twitter, Instagram, Telegram n [| AI |] Telegram n [| Human |]'}/r/n/r/n, 'I don't know if the flash attention can be longer and reach 2048?
It's possible but without flash attention it will consume too much VRAM.
Anyone get this working? I saw the monkey patch in the README, has anyone tried training multi-round conversation?
Yamashi got it working
is the model out there available for using it?
Well, this is what vicuna does. If you want to see it in action check out vicuna's published weights. (It's quite impressive compared to alpaca)
Is it possible to use flash attention, in order to fine-tune with longer conversations instead of just a question-and-answer?