From f8713c089be7b1531663a461a76aa5794a4f1830 Mon Sep 17 00:00:00 2001 From: James Ravenscroft Date: Sun, 9 Apr 2023 17:56:27 +0100 Subject: [PATCH] add readme --- README.md | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index f657200..b9dda09 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ cd ggml mkdir build cd build cmake .. -make codegen +make codegen codegen-quantize ``` ## Getting The Models @@ -24,4 +24,14 @@ Start by downloading either the [2B](https://huggingface.co/moyix/codegen-2B-mul python convert-codegen-to-ggml.py ./codegen-6B-multi-gptj 0 ``` -## Build GGML \ No newline at end of file +## Quantize the model + +```bash +./bin/codegen-quantize ../../codegen-6B-multi-gptj/ggml-model-f32.bin ../../codegen-6B-multi-gptj/ggml-model-quant.bin 2 +``` + +## Run the model + +```bash +./bin/codegen -t 6 -m ../../codegen-6B-multi-gptj/ggml-model-quant.bin -p "def main(" +``` \ No newline at end of file