From 960980247f4737be2a952b8a6055b95e7f1dd46f Mon Sep 17 00:00:00 2001
From: cal066 <60696996+cal066@users.noreply.github.com>
Date: Fri, 25 Aug 2023 14:33:04 +0000
Subject: [PATCH] ctransformers: gguf support (#3685)

---
 modules/models.py | 11 ++++++++++-
 requirements.txt  |  2 +-
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/modules/models.py b/modules/models.py
index 48a384cf..ea9cc528 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -280,7 +280,16 @@ def ctransformers_loader(model_name):
         if path.is_file():
             model_file = path
         else:
-            model_file = list(Path(f'{shared.args.model_dir}/{model_name}').glob('*.bin'))[0]
+            entries = Path(f'{shared.args.model_dir}/{model_name}')
+            gguf = list(entries.glob('*.gguf'))
+            bin = list(entries.glob('*.bin'))
+            if len(gguf) > 0:
+                model_file = gguf[0]
+            elif len(bin) > 0:
+                model_file = bin[0]
+            else:
+                logger.error("Could not find a model for ctransformers.")
+                return None, None
 
     logger.info(f'ctransformers weights detected: {model_file}')
     model, tokenizer = ctrans.from_pretrained(model_file)
diff --git a/requirements.txt b/requirements.txt
index daccd5dd..90c7969f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -41,4 +41,4 @@ https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 
 # ctransformers
-https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.23+cu117-py3-none-any.whl
+https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.24+cu117-py3-none-any.whl