-
### 🚀 The feature
Allowing for the use of additional models available via HF.
### Motivation, pitch
Hi, I would like to test models as they are being released on HF for efficacy on a variety of dat…
-
Publishing a LLM named vicuna-13b is correct, but switching to another LLM Baichuan-13B-Chat gives me an error
I have downloaded Baichuan-13B-Chat from Huggingface and tested OK.Now I put LLM like …
-
Try to load a local GPTQ model, and get the following error:
```
Traceback (most recent call last):
File "/home/ubuntu/temp/test.py", line 3, in
llm = AutoModelForCausalLM.from_pretrained…
-
Hello there,
I tried to change the original model to guanaco-33d (also tried with the 65-b) but I always end up having the error "Task not found in this model".
Here's what I changed in the .e…
-
### Describe the bug
I have used this command instead of using old Cuda in my ipynb
`!git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa`
Now, I ran the server using following code -
…
-
### System Info
PyTorch version: 2.0.1
CUDA used to build PyTorch: 11.8
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: Could not collect
…
-
### System Info
I was trying to run gradio with text-generation, seems this a problem in most spaces:
example: https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi
supposed to return te…
-
The HTTP API fails while **the chat option works**
curl http://chat.petals.ml/api/v1/generate -H "Content-Type: application/x-www-form-urlencoded" -d 'inputs="A cat in French is "&max_new_tokens=3…
-
### System Info
Docker version: latest and 0.8 tested
Tested on runpods directly via docker container
command: --model-id TheBloke/guanaco-7B-HF
### Information
- [X] Docker
- [ ] The C…
-
### Bug description
After the latest release (0.1.3), I'm facing an issue with models not generating complete text.
I have tested multiple models (6), and it seems the issue is in the rendering of r…