stanford_alpaca · Issues· 186 open

why dose my finetuned model repeat the given prompt before generating its response

I have a question regarding the VRAM requirements for fine-tuning a 7B model.

Alpaca problem solving team - QQ chat group

ValueError: Your setup doesn't support bf16/gpu. You need torch>=1.10, using Ampere GPU with cuda>=11.0

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 0

error of multi-GPU: torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 0

bf16 & tf32，can they be used together

Tensors of the same index must be on the same device and the same dtype except `step` tensors that can be CPU and float32 notwithstanding

train.py fails with TypeError: Object of type Tensor is not JSON serializable

Keyword arguments {'add_special_tokens': False} not recognized.

ValueError: Trying to set a tensor of shape torch.Size([32769536]) in "weight" (which has shape torch.Size([32001, 4096])), this looks incorrect.

SFT Mistral；

Any plans for using GPT-4 for self-instruct? Or using larger llama models?

How to finetune with a own private data and then build chatbot on that?

weight_diff.py state_dict_recovered[key].add_(state_dict_raw[key]) RuntimeError: The size of tensor a (32001) must match the size of tensor b (32000) at non-singleton dimension 0