Non quantized GGUF version of the model : Trelis/Llama-2-7b-chat-hf-function-calling-v3

The 8-bits quantized and 4-bits quantized models fail to understand which arguments are required and which are optionals

Downloads last month
0
GGUF
Model size
6.74B params
Architecture
llama
Inference Examples
Unable to determine this model's library. Check the docs .