-
For some reason, I'm not able to get streaming response in chainlit UI although I do get streaming output normally in console. @willydouhard
This is my code:
# Imports
from langchain import Hu…
-
I get the same error when Falcon 7B pod starts. Looks like the model file was deleted: https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-7B-GGML/commit/7343df6eea4cfef162077380d075b49fdc9364e…
-
### Feature request
How can we take advantage of https://github.com/bentoml/OpenLLM ?
### Motivation
_No response_
-
When I initialize [this MPT model ](https://huggingface.co/TheBloke/MPT-7B-GGML) as an LLM and connect it to a ConversationChain the status indicator turns green:
However, when I open the cha…
-
I tried loading both `Thor.json` and `Evelyn.json`.
https://zoltanai.github.io/character-editor/
-
### Describe the bug
When try to load the model in the UI, getting error: AttributeError: 'LlamaCppModel' object has no attribute 'model'
(Also for more knowledge, what are these stands for: Q#_K_…
Ege-P updated
10 months ago
-
Hey! Thanks for this library, I really appreciate the API and simplicity you are bringing to this, it's exactly what I was looking for in trying to integrate ggml models into python! (specifically int…
-
Hi,
I need to use the embed functionality in pgml 2.6+ in PostgreSQL-14, I [built from sources for Linux](https://postgresml.org/docs/guides/setup/v2/installation) the pgml extension on my ubuntu 2…
-
### Describe the bug
When performing this after fine tuning a model:
def load_model(xtts_checkpoint, xtts_config, xtts_vocab):
global XTTS_MODEL
clear_gpu_cache()
if not xtts_checkp…
-
I'm Running Wizard-Mega-13B-ggml using ctransformers on Google Colab. it Works Fine.
But After Sometimes, When I'm running the Same Code it Gives me This Error
```
Failed to create LLM 'llama' …