From b00e2d90f9e61113e12155ba850c2fc59607b251 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Tr=E1=BA=A7n=20=C4=90=E1=BB=A9c=20Nam?= Date: Fri, 22 Dec 2023 15:18:52 +0700 Subject: [PATCH] fix: readme --- awqpy/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/awqpy/README.md b/awqpy/README.md index 8d119df46..6ede7b8b9 100644 --- a/awqpy/README.md +++ b/awqpy/README.md @@ -43,7 +43,7 @@ Example for llama model # For llama7b and llama2 models python convert.py models/llama-7b/ --awq-path awq_cache/llama-7b-w4-g128.pt --outfile models/llama_7b_fp16.gguf # For mistral and mpt models -python convert-hf-to-gguf.py models/llama-7b/ --awq-path awq_cache/llama-7b-w4-g128.pt --outfile models/llama_7b_fp16.gguf +python convert-hf-to-gguf.py models/mpt-7b/ --awq-path awq_cache/llama-7b-w4-g128.pt --outfile models/mpt_7b_fp16.gguf ``` ## Quantize @@ -57,7 +57,7 @@ python convert-hf-to-gguf.py models/llama-7b/ --awq-path awq_cache/llama-7b-w4-g # For llama and llama2, and mistral models. ./build/bin/main -m models/llama_7b_q4_0.gguf -n 128 --prompt "Once upon a time" # For mpt models. -./build/bin/main -m models/llama_7b_q4_0.gguf -awq -n 128 --prompt "Once upon a time" +./build/bin/main -m models/mpt_7b_q4_0.gguf -awq -n 128 --prompt "Once upon a time" ``` ## Benchmark