Ali F
Ali F
@NamburiSrinath try this: 1. Create a new python env 2. Install torch with pip 3. Install AutoAWQ from source but with `--no-build-isolation` argument
I also added this feature to [my fork](https://github.com/Ali-Flt/ollama-telegram). Using a whisper docker container.
Did you even read the README?
running this command from the README should generate a .npz file including the sampled images. You can modify the `image_sample.py` code if you want to store the samples differently. ```python...
You should: 1. Create a python environment (if you don't know how look it up it's easy) 2. In your created environment install this repository: `pip install -e .` 3....
The android app crashes for me when I hit connect. Phone: Samsung Galaxy A70
I think this fixes it: ```python async def add_prompt_to_active_chats(message, prompt, image_base64, modelname, system_prompt=None): async with ACTIVE_CHATS_LOCK: # Prepare the messages list messages = [] # Add system prompt if provided...
@lemassykoi the code is wrong and does not append the system prompt to the beginning of the conversation. My modification fixes it.
This feature is crucial for such always-running tasks that take GPU memory when idle. I usually do this by creating a separate child process for each model run so that...
@RBEmerson970 some people myself included run these services on machines that are used for multiple purposes and by multiple people. The same machine might be used for other GPU intensive...