From 0687a3092b50a30fc02d43f7d32644da5444efef Mon Sep 17 00:00:00 2001 From: Ihsan Soydemir Date: Tue, 25 Jul 2023 20:49:44 +0200 Subject: [PATCH] Fix typo in 70B path --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0e6f218..ea1e07f 100644 --- a/README.md +++ b/README.md @@ -140,7 +140,7 @@ llm = Llama(model_path="./models/7B/ggml-model.bin", n_ctx=2048) Llama2 70b must set the `n_gqa` parameter (grouped-query attention factor) to 8 when loading: ```python -llm = Llama(model_path="./models/7B/ggml-model.bin", n_gqa=8) +llm = Llama(model_path="./models/70B/ggml-model.bin", n_gqa=8) ``` ## Web Server