-
Hi,
Has anyone else seen this in the debug?
`[?25l[2J[m[HWindows PowerShell
Copyright (C) Microsoft Corporation. All rights reserved.[4;1HInstall the latest PowerShell for new features and i…
-
"We tested the speculative inference using the first 100 inputs from alpaca test dataset as prompts. When model=gpt2-xl, draft_model=gpt2".
I want to test speedup for my own model and draft_model. …
-
The weights downloaded via
curl -o ggml-alpaca-7b-q4.…
-
Hi, seems that this use the standard alpaca 7B weights. But when I use this weights with llama.cpp it seems to be “censored”.
So what is the Pre Prompt or how to make use this in the same way with …
-
What is the science behind the seed questions? If you added, say, 10% poetry, would the resulting set of 57,500 instructions produce an alpaca that was better at poetry? Have people tested different …
-
Llamax code it knows how to handle alpaca formatted QA data, but I didnt' see anything in there to handle ShareGPT format data,
How do I finetune with the new format? Your finetune guide (https://…
-
Why do we do this? I assume this is removing the EOS token. I don't see this happening in the training code from Stanford. Thanks for your time
-
For example, it still uses old syntax for `convert-pth-to-ggml.py`, and for `export-from-huggingface.py`. Also maybe it would be better to clarify that even when installing through pip, we still need …
-
I'm running alpaca on my Intel Xeon Silver 4214(4) @ 2.194GHz and I'm having a lot of s…
-
File "/home/AI/alpaca-lora/export_state_dict_checkpoint.py", line 68, in unpermute
w.view(n_heads, 2, dim // n_heads // 2, dim).transpose(1, 2).reshape(dim, dim)
RuntimeError: shape '[32, 2, 6…