Bringing support for local inference of audio language models (that was previously not available). Different from voicechat2, because this includes quantizations of the Qwen2-Audio models, and releases them as a GGUF modelfile.
Bringing support for local inference of audio language models (that was previously not available). Different from voicechat2, because this includes quantizations of the Qwen2-Audio models, and releases them as a GGUF modelfile.