This is the llama.cpp GGUF Quantised version of Hermes 2 Pro Llama-3 8B from Nous Research with function calling capabilities.

8B

660 Pulls Updated 4 months ago

2 Tags
1451afe6947f • 5.7GB • Updated 4 months ago
0d517b216f9f • 6.6GB • Updated 4 months ago