-
@marella Is it possible to load and run any of the RedPajama variants? I have tried several variations of the following in Google Colab, but all of them cause the session to crash:
```
from ctransfo…
-
Traceback (most recent call last):
File "/home/ec2-user/spacy/spacy.py", line 8, in
from spacy_llm.util import assemble
File "/home/ec2-user/.conda/envs/naitik2/lib/python3.10/site-package…
-
### Describe the bug
I use [text-generation-webui](https://github.com/oobabooga/text-generation-webui) and use [llama.cpp](https://github.com/ggerganov/llama.cpp) as loader for the GGML format La…
-
Hi! I'm trying to install flash attention with PyTorch nightly.
The command I'm running is
```bash
pip install flash-attn==2.3.5 --no-build-isolation
```
```python
Killed
[46/…
-
The response of a query is incomplete. ChatGPT3.5 allows users to prompt it to continue with the response in a new prompt and the team at Oobabooga added a "Continue" button to their WebUI to do the s…
-
### Describe the bug
When starting the text-generation-webui using start_windows.bat from the command prompt using the defaults, the interface doesn't render correctly. On Edge and Chrome it doesn't…
-
Messed with thread parameter to see if reducing number of threads would help. No dice
-
There is CLBlast GPU support for GPT-2 based models on koboldcpp for example, where I can do prompt processing on the GPU VRAM for less prompt batching errors with my 16GB of CPU RAM. Does anyone know…
-
Hi there. The llamacpp is now supporting q2 quantization. Is there any chance this comes to ctransformers?
-
Had to go code diving to work out what --model-type was meant to be. Can we please have the docs for the command line parameters in an appropriate place in the wiki?