His base GGML quants for Llama 2 & CodeLlama (There is no 34B GGML for CodeLlama)
Victor Risgaard
lallesx
·
AI & ML interests
Large Language Models (LLM's)
Organizations
None yet
His base GGUF quants for Llama 2 & CodeLlama
-
TheBloke/Llama-2-7B-GGUF
Text Generation • 7B • Updated • 19.1k • 207 -
TheBloke/Llama-2-7B-Chat-GGUF
Text Generation • 7B • Updated • 72.1k • 518 -
TheBloke/Llama-2-13B-GGUF
Text Generation • 13B • Updated • 6.56k • 70 -
TheBloke/Llama-2-13B-chat-GGUF
Text Generation • 13B • Updated • 9.4k • 206
His base GGML quants for Llama 2 & CodeLlama (There is no 34B GGML for CodeLlama)
His base GGUF quants for Llama 2 & CodeLlama
-
TheBloke/Llama-2-7B-GGUF
Text Generation • 7B • Updated • 19.1k • 207 -
TheBloke/Llama-2-7B-Chat-GGUF
Text Generation • 7B • Updated • 72.1k • 518 -
TheBloke/Llama-2-13B-GGUF
Text Generation • 13B • Updated • 6.56k • 70 -
TheBloke/Llama-2-13B-chat-GGUF
Text Generation • 13B • Updated • 9.4k • 206
datasets 0
None public yet