mvuthegoat comments

Results 4 comments of


                                            mvuthegoat

Stuck on training: Created a PretokDataset with rng seed 42

I have a side question, when will the while loop in the `def __iter__(self)` function of PretokDataset break? https://github.com/karpathy/llama2.c/blob/c7a26264a233c32f396b1c67be4ac019d2d8a659/tinystories.py#L206-L223

Hello everyone, can we perform Lora or other fine-tuning based on the Vicuna model? How much graphics memory is required?

> As for 7B model, LoRA consumes about 17GB gpu memory. If it consumes only 17GB, why did I get this message? OutOfMemoryError: CUDA out of memory. Tried to allocate...

Finetune leads to ValueError: Expected a cuda device, but got: cpu

> have you been able to resolve this? I'm facing the same issue

Fine-tuning Vicuna-7B with Local GPUs: RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false

> I successfully resolved the error and completed the training, **but the result seems incorrect.** > > > I'm facing similar issue > > `Expected q_dtype == torch::kFloat16 || ((is_sm8x...