kostum123
kostum123
I am not saying that this task is easy and the goals are simple, but if the accelerations in training time and decreases in VRAM memory usage promised by Unsloth...
Is this going to merge anytime soon?
same issue. i tried this and now it doesnt give error but still generated image irrelevant. still broken. How can i check s.diff launch options on colab so i can...
GPT3.5 and GPT4 for comparision for this promt: Write c++ code, fully compatible with Arduino IDE, with detailed comments, to blink an LED on pin 6 once every two seconds....
Same for me. Its stuck at "noise points (42.3%) will be assigned to nearest cluster." Also bge m3 cant be used for clustering model, lilac defaults to weak model that...
> We just added `dataset.cluster(skip_noisy_assignment=...)` (UI support too) in #1194 > > When set to True, it will skip assigning noisy points to the nearest cluster to speedup clustering. This...
Qlora will be a great addition to these project.
Can we merge this? in current form liger kernel broken.
> Thank you @winglian for raising the issue! Looks like FLCE fails at torch autograd when we make embedding + peft layer trainable together. We are happy to take a...
> We usually do not adopt a diagonal attention mask during pre-training, since we expect the model to have the largest context length at each optimization step. The thing is,...