From 27d53589ff884559919b4bd2c40690223feaaffa Mon Sep 17 00:00:00 2001 From: Jon Craton Date: Fri, 21 Jun 2024 12:10:15 -0400 Subject: [PATCH] docs: Update readme examples to use newer Qwen2 model (#1544) --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4c37ba3..4a710d4 100644 --- a/README.md +++ b/README.md @@ -327,7 +327,7 @@ You'll need to install the `huggingface-hub` package to use this feature (`pip i ```python llm = Llama.from_pretrained( - repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF", + repo_id="Qwen/Qwen2-0.5B-Instruct-GGUF", filename="*q8_0.gguf", verbose=False ) @@ -688,7 +688,7 @@ For possible options, see [llama_cpp/llama_chat_format.py](llama_cpp/llama_chat_ If you have `huggingface-hub` installed, you can also use the `--hf_model_repo_id` flag to load a model from the Hugging Face Hub. ```bash -python3 -m llama_cpp.server --hf_model_repo_id Qwen/Qwen1.5-0.5B-Chat-GGUF --model '*q8_0.gguf' +python3 -m llama_cpp.server --hf_model_repo_id Qwen/Qwen2-0.5B-Instruct-GGUF --model '*q8_0.gguf' ``` ### Web Server Features