Introduction
Introduction Statistics Contact Development Disclaimer Help
Doubling the 69 tokens for gpt. Double the fun! - annna - Annna the nice friend…
git clone git://bitreich.org/annna/ git://enlrupgkhuxnvlhsf6lc3fziv5h2hhfrinws6…
Log
Files
Refs
Tags
README
---
commit 0107c05ab6aa8d995308bd36a20b447c1517b2d4
parent eec5030ed1541bcce3a6a268521c2dc3e7b9e6ae
Author: Annna Robert-Houdin <[email protected]>
Date: Wed, 25 Dec 2024 08:47:30 +0100
Doubling the 69 tokens for gpt. Double the fun!
Diffstat:
M gpt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
---
diff --git a/gpt b/gpt
@@ -6,7 +6,7 @@ ggmlbase="/br/ai/llama.cpp"
ggmlbin="./build/bin/llama-cli"
#ggmlmodel="models/gpt-2-1558M/ggml-model.bin"
ggmlmodel="models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
-ggmlntokens="69"
+ggmlntokens="$((69 * 2))"
cd $ggmlbase
prompt="$1"
You are viewing proxied material from bitreich.org. The copyright of proxied material belongs to its original authors. Any comments or complaints in relation to proxied material should be directed to the original authors of the content concerned. Please see the disclaimer for more details.