Add GGUF convertation support
#12
by Naster17 - opened
Add GGUF convertation support. So we can use llama.cpp llama-tts and other ggml projects
python3 convert_hf_to_gguf.py --verbose --outtype f16 --outfile ~/Downloads/models/qwen3-tts-1.7b-base-f16.gguf ~/Downloads/models/TTS/Qwen3-TTS-12Hz-1.7B-Base/speech_tokenizer/ --no-lazy
INFO:hf-to-gguf:Loading model: speech_tokenizer
WARNING:hf-to-gguf:Failed to load model config from /home/nik/Downloads/models/TTS/Qwen3-TTS-12Hz-1.7B-Base/speech_tokenizer: The checkpoint you are trying to load has model type `qwen3_tts_tokenizer_12hz` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: Qwen3TTSTokenizerV2Model
ERROR:hf-to-gguf:Model Qwen3TTSTokenizerV2Model is not supported
If use default llama.cpp converter