From 8d195efddab0ac5a85c805e377d285c079557b9d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=2E=20Yusuf=20Sar=C4=B1g=C3=B6z?= Date: Wed, 27 Sep 2023 17:51:40 +0300 Subject: [PATCH] Add gguf to requirements + fix typo --- README.md | 2 +- models/requirements.txt | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index d355795..ad57a1b 100644 --- a/README.md +++ b/README.md @@ -76,7 +76,7 @@ pip install -r requirements.txt 4. Use `models/convert_hf_to_gguf.py` to convert it to GGUF format: ```shell -python convert_hf_to_gguf.py ../../CLIP-ViT-B-32-laion2B-s34B-b79K +python convert_hf_to_gguf.py -m ../../CLIP-ViT-B-32-laion2B-s34B-b79K ``` The output `CLIP-ViT-B-32-laion2B-s34B-b79K_ggml-model-f16.bin` file is in the model directory specified in the command above. diff --git a/models/requirements.txt b/models/requirements.txt index 4f492dd..f70f0e2 100644 --- a/models/requirements.txt +++ b/models/requirements.txt @@ -1,2 +1,3 @@ torch transformers +gguf