c4ai-command-r-plus-GGUF / command-r-plus-Q5_K_M-00001-of-00002.gguf

Commit History

BPE pre-tokenization for Q5_K_M variant
ebeb1fd

pmysl commited on

Add chat template to Q5_K_M variant
05026af

pmysl commited on

Update Q5_K_M variant
752f576

pmysl commited on

Use llama.cpp compatible split for Q5_K_M variant
996fdaa

pmysl commited on

Rename files
3ec98d7

pmysl commited on

Remove experimental weights
7fc82e0

pmysl commited on

Add Q5_K_M variant
0c3dcc8

pmysl commited on