VDrontV2
Collection
4 items • Updated
cc0-1.0
Dront Quant - VDC-team/DrontGPTQ
VDrontV2-0.1b
🦤 Dront Quant 16 bit
🦤 Dront Quant 8 bit
To use the model, go to the folder named after the model and download the relevant .dq file. Then, download DQuse.py and replace the model name in the line(388 chat_with_dq_model("model.dq", 64)) with the path to the model.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support