-
The error occurs when I call the LLMEngine object.
The error below appears.
```
ValueError: When using LoRA, vocab size must be 32000 >= vocab_size
-
### Issue Feedback
- [X] I confirm that I have searched for a solution to this issue in the [FAQ](https://aiodoc.physton.com/FAQ.html) and couldn't find a solution.
- [X] I confirm that I have search…
-
Hey there!
There's an incredibly powerful extension for A1111 called Dynamic Lora Weights which allows one to control the weights of the lora at any given step during the whole generation. For instan…
-
If using LORA within region prompts, it will trigger each LORA to reload once per step. If using it in the main prompt, it reloads each step as well when switching prompts, even though it's the same L…
-
Line 62 and 63 of LORA_GUI.py refer to the "images" directory as "Images", and so won't run
-
sample images when training it looks like subject.
when trying in forge it doesn't load. i trained the clip l text encoder along with it. but doesn't work in forge or comfy
-
### Expected Behavior
to work
### Actual Behavior
does not work
### Steps to Reproduce
load the lora as normal and prompt for it
### Debug Logs
```powershell
on the image
```
### Other
_…
-
### 🚀 The feature, motivation and pitch
Speculative decoding has demonstrated significant potential in efficiently generating proposals and utilizing idle computing power to expedite the auto-regress…
-
Can someone please help me figure out why inpainting is not working for me while basic image generation seems to be working?
I have a folder with 500 images of an identity sampled from a few videos…
-
发生异常: ValueError
Can't read templates/alpaca.json
File "/home/ww/alpaca-lora-hua/alpaca-lora/utils/prompter.py", line 20, in __init__
raise ValueError(f"Can't read {file_name}")
File "/hom…