top | item 40065674 (no title) clementmas | 1 year ago I'm considering switching my function calling requests from OpenAI's API to Mistral. Are they using similar formats? What's the easiest way to use Mistral? Is it by using Huggingface? discuss order hn newest ru552|1 year ago easiest is probably with ollama [0]. I think the ollama API is OpenAI compatible.[0]https://ollama.com/ talldayo|1 year ago Most inference servers are OpenAI-compatibile. Even the "official" llama-cpp server should work fine: https://github.com/ggerganov/llama.cpp/blob/master/examples/... pants2|1 year ago Ollama runs locally. What's the best option for calling the new Mixtral model on someone else's server programmatically? load replies (1)
ru552|1 year ago easiest is probably with ollama [0]. I think the ollama API is OpenAI compatible.[0]https://ollama.com/ talldayo|1 year ago Most inference servers are OpenAI-compatibile. Even the "official" llama-cpp server should work fine: https://github.com/ggerganov/llama.cpp/blob/master/examples/... pants2|1 year ago Ollama runs locally. What's the best option for calling the new Mixtral model on someone else's server programmatically? load replies (1)
talldayo|1 year ago Most inference servers are OpenAI-compatibile. Even the "official" llama-cpp server should work fine: https://github.com/ggerganov/llama.cpp/blob/master/examples/...
pants2|1 year ago Ollama runs locally. What's the best option for calling the new Mixtral model on someone else's server programmatically? load replies (1)
ru552|1 year ago
[0]https://ollama.com/
talldayo|1 year ago
pants2|1 year ago