declare-lab/flan-alpaca

Issues

• Performance of the model on gsm8k/SVAMP/MultiArith.

  #22 opened a year ago by hccngu
  1

• Any plan to support trl-peft load_in_8bit for training.py ?

  #21 opened a year ago by the-unsoul
  1

• Loss value is NaN

  #19 opened a year ago by liuqingli
  3

• Unable to train on 4-5 gtx 1070s

  #17 opened a year ago by sfxworks
  10

• unable to use new flan-alpaca-gpt4-xl in pipeline

  #20 opened a year ago by andreynikk
  2

• OMP: Error #100: Fatal system error detected.

  #16 opened a year ago by sfxworks
  1

• I dont see any progress logs

  #6 opened a year ago by allthingssecurity
  1

• Trouble training

  #5 opened a year ago by KurtFeynmanGodel
  2

• RuntimeError: Trying to resize storage that is not resizable

  #4 opened a year ago by allthingssecurity
  1

• What are the available parameters for generator?

  #1 opened a year ago by sungkim11
  1

• Quantized

  #2 opened a year ago by naturallydeer
  1

• Usage example in readme doesn't work

  #18 opened a year ago by sfxworks
  2

• Performance on MMLU

  #13 opened a year ago by allanj
  6

• Commercial Use?

  #3 opened a year ago by avb-is-me
  2

• wget https://raw.githubusercontent.com/tloen/alpaca-lora/main/alpaca_data_cleaned.json -O data/alpaca_clean.json

  #15 opened a year ago by kizombaciao
  3

• Flan Data

  #12 opened a year ago by ekurtulus
  2

• In ShareGPT, why the conversation from human is accumulated?

  #11 opened a year ago by qmpham
  5

• LoRA + FSDP -- issue

  #10 opened a year ago by ngun7
  2

• issue in training declare-lab/flan-alpaca-base model

  #8 opened a year ago by p1yush99
  2

• is there any plan for flan-ul2?

  #9 opened a year ago by nonkung51
  6

• use gpt4all dataset

  #7 opened a year ago by Shiro836
  4