akemi/noway.moe
1
0
Fork 0
Code Issues 1 Pull requests Packages Projects Releases Wiki Activity

Llamas: update urls

Browse source
This commit is contained in:
Akemi Izuko 2023-12-31 18:43:19 -07:00
parent cc01691a33
commit c26ad07c69
Signed by: akemi
GPG key ID: 8DE0764E1809E9FC
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/content/llama/a-history-of-llamas.md
View file

@ -102,7 +102,7 @@ VRAM, which meant many home computers could now run 4-bit quantized 7B models!
Previously, most enthusiasts would have to rent cloud GPUs to run their "local" Previously, most enthusiasts would have to rent cloud GPUs to run their "local"
llamas. Quantizing into GGUF is a very expensive process, so llamas. Quantizing into GGUF is a very expensive process, so
[TheBloke](https://huggingface.co/TheBloke) on Huggingface emerges the defacto [TheBloke](https://huggingface.co/TheBloke) on Huggingface emerges the defacto
source for pre-quantized llamas. source for [pre-quantized llamas](../quantization).
Based on LLaMa, the open source Based on LLaMa, the open source
[llama.cpp](https://github.com/ggerganov/llama.cpp) becomes the leader of local [llama.cpp](https://github.com/ggerganov/llama.cpp) becomes the leader of local