laoda513

是否支持量化的模型呀？

4

你好，请问是否支持量化的模型，比如gptq？ 如果可以的话，按照比例计算的话，我有8张24g的显卡的话，用流水线并行，是不是可以lora 175b版本量化模型了？ 谢谢~

not support lora with autogptq/peft?

5

Sorry, I'm a little confused. It seems that the project is unable to load LORA trained by the autogptq project. However, it can load LORA trained by alpaca-lora-4bit. Here's my...

[Usage]: How to disable multi lora to avoid using punica ? Or is the punica being the only choice?

3

I searched the outdated issues, and everyone is saying that the version of multi lora's punica must be >=8.0. Therefore, I want to ask if there is an option that...

Might be a bug of hibrid engine : In Step3 wrong generation secquence when hibrid engine is enabled.

7

When using where using hybrid engine, The output sequence always be 'a a a a ', while if I disabled hybrid engine，the output sequence is correct here is my log...

The reward in step3 seems to be completely random without any noticeable increase.

10

I am testing the 1.3B training. Steps 1 and 2 have already passed, but there is no change in reward after completing step 3. I used LoRa to train for...

great work. seems more efficient than pp in my machine (8*2080ti 22g) I am thinking about if this can work with zero or, forexample to combine 2 gpu to 1,...

pippy.SaveModule not exist？

2

In examples/checkpoint/toy_model.py `from pippy.compile import compile_stage from pippy.SaveModule import save_checkpoint` which is not exist?