after loading the models you can merge into a single file .\llama.cpp\build\bin\Release\llama-gguf-split.exe --merge .\mymodels\model_name-00001-of-00004.gguf .\mymodels\model_name-merged.gguf
base model: https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp
- Downloads last month
- 356
Hardware compatibility
Log In
to view the estimation
4-bit
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for FBTMAML/KAT-Dev-72B-Exp
Base model
Kwaipilot/KAT-Dev-72B-Exp