This is a quantized GGUF version of Orca-2 7B and 13B quantized to 4_0 and 8_0 bits.
(link to the original model : https://www.microsoft.com/en-us/research/blog/orca-2-teaching-small-language-models-how-to-reason/)
- Downloads last month
- 16
This is a quantized GGUF version of Orca-2 7B and 13B quantized to 4_0 and 8_0 bits.
(link to the original model : https://www.microsoft.com/en-us/research/blog/orca-2-teaching-small-language-models-how-to-reason/)