-
### Environment
🪟 Windows
### System
Firefox Version 128.01.12.3
### Version
1.12.3
### Desktop Information
_No response_
### Describe the problem
Steps to reproduce:
1. Launch SillyTavern a…
-
**Is your feature request related to a problem? Please describe.**
I see quite some GPT-2 implementations, but I am missing a GPT-Neo/GPT-J implementation. This is a variant of GPT-2 which is quite s…
-
May 13, 2023, 5:57PM EST
With latestgptq branch, the MPT 7B model successfully loads on my RTX 3060 12GB, but on prompting to generate text, an error occurs involving bfloat16. Pastebin of error is…
-
When using Whisper model (ggml-tiny-en.bin) in KoboldAI Lite frontend (SillyTavern works perfectly well with the same Whisper loaded through KoboldCpp), a window shows 'Error while submitting prompt: …
-
Currently your project requires users to manually install python and some other dependencies for the venv, this can be simplified with micromamba. Micromamba is a standalone C++ version of Conda that …
-
https://github.com/oobabooga/text-generation-webui/ can be used as a back-end to run dozens of different local models, including the latest LLaMA model. (LLaMA-13B beats GPT-3.5 in benchmarks while f…
-
To some extent it seems GPT-J 6B might be useful to assist with writing code in many languages; but with Python, tabs and spaces at the beginning of lines matter, and unfortunately, the way it works n…
-
### System Info
- `transformers` version: 4.44.2
- Platform: Linux-6.8.0-44-generic-x86_64-with-glibc2.39
- Python version: 3.12.3
- Huggingface_hub version: 0.24.7
- Safetensors version: 0.4.5…
-
when i try to download models, i get this error
```
OSError: None is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private reposit…
-
This may be part of a larger issue of action indices getting corrupted, but it's 100% reproducible for me so it may be an easy way to debug that issue. It might instead be chat specific due to the way…