Saifeddine ALOUI
Saifeddine ALOUI
Hi. The API allows me to list the local models. Is there a way to list all available models (those we can find in the website of ollama? I need...
Hi there. I wonder if you are planning on supporting windows. I can use wsl and it runs fine ,but a more native version is better. I see that uvloop...
### What are you trying to do? I would like to propose the addition of tokenize and detokenize endpoints to the Ollama server. This feature is crucial for the Ollama...
Hi, CodeLlama2 is not really working on exllama. The answers are sometimes complete gibbrish. Can you please upgrade the library to upgrade to the new rope_thea parameter of CodeLlama ?...
 Hi, I was prompting llama-2-7B and got into this error. Can you please handle the case there are nans in the logits?
We will add a plugin system for people to build their custom add-ons to the project.
Today A new version of the LLamaCpp bindings have been added. We are going to move to this new binding system by tomorrow.
It would be a good idea to add a button for regenerate and stop the current generation.
Currently those options can be changed when calling the application: --temp: the sampling temperature for the model (default: 0.1) --n-predict: the number of tokens to predict at a time (default:...
Al discussions are stored in a local qslite3 database. It would be a good thing to add a left bar with the list of discussions so that people can reopen...