rvsh2
rvsh2
I wanted to test WhisperFusions on rtx3090. Went throught build.sh and then: `docker run --gpus all --shm-size 64G -p 6006:6006 -p 8888:8888 -it ghcr.io/collabora/whisperfusion:latest ` and I run http server...
### What are you trying to do? Hi, Are there any plans to incorporate RyzenAi into Ollama? It would be great breakthrought in running larger models. As in demo from...
### What are you trying to do? Many models are very good with specific tasks but they lack support of other languages. Their output in other language than english is...
**Is your feature request related to a problem? Please describe.** The problem with many models is that they are good only in english language. **Describe the solution you'd like** There...
Hello, I have problems with using function_calling with local llm's. I tried ten's of models but none is working correctly. I have found functionary v2.4 as one that has the...
Hi, Could you add polish language in the future? There is no good TTS for polish. Please consider this. Many thanks.
Hi, Is there an api server compatible with openai response type for faster whisper? I'm looking in the opensource space but can't find anything appropiate like this for standard whisper:...
Hello, Is there a possibility to run ollama with functionary small v2.4? It it very good model for tool calling. BR Krzysztof
Hello, I run this code as an example: ``` chat.register(get_car_price) # register this function chat.register(get_top_stories) # register this function chat.register(what_time) chat.register(get_current_weather,weather_parameters) async def main(): await chat.submit("What is the weather in...
Hi, Is there a possibiliy to add additional layers for translation model: 1. INPUT: Translation model from any language to English 2. MIDDLE: Intent model (eg. ChatGpt, ollama models) 3....