I hope that something similar emerge on Linux.

SYCL can be a candidate, like Vulkan for 3D Acceleration: it’s a PITA to deal with CUDA, ROCm etc etc.

Currently all the finetuned version of Mistral I’ve tested have a high rate of hallucination: this one also seems to have this tendency.

Added also to Ollama library: in case of need.

https://ollama.ai/fakezeta/neural-chat-7b-v3-1