Update default model to bartowski/Qwen2.5-7B-Instruct-GGUF/Qwen2.5-7B-Instruct-Q8_0.gguf

Author: daavoo

demo/app.py

@@ -13,7 +13,7 @@
 @st.cache_resource
 def load_model():
     return load_llama_cpp_model(
-        "bartowski/Qwen2.5-3B-Instruct-GGUF/Qwen2.5-3B-Instruct-f16.gguf"
+        "bartowski/Qwen2.5-7B-Instruct-GGUF/Qwen2.5-7B-Instruct-Q8_0.gguf"
     )
 
 

example_data/config.yaml

@@ -1,7 +1,7 @@
 question: "What optimizer was used to train the model?"
 input_file: example_data/1706.03762v7.pdf
 output_dir: example_outputs/1706.03762v7.pdf
-model: "bartowski/Qwen2.5-3B-Instruct-GGUF/Qwen2.5-3B-Instruct-f16.gguf"
+model: "bartowski/Qwen2.5-7B-Instruct-GGUF/Qwen2.5-7B-Instruct-Q8_0.gguf"
 find_prompt : |
   You are given two pieces of information:
   1. A list of valid section names.

src/structured_qa/cli.py

@@ -16,7 +16,7 @@ def structured_qa(
     input_file: str | None = None,
     output_dir: str | None = None,
     model: str
-    | None = "bartowski/Qwen2.5-3B-Instruct-GGUF/Qwen2.5-3B-Instruct-f16.gguf",
+    | None = "bartowski/Qwen2.5-7B-Instruct-GGUF/Qwen2.5-7B-Instruct-Q8_0.gguf",
     find_prompt: str = FIND_PROMPT,
     answer_prompt: str = ANSWER_PROMPT,
     from_config: str | None = None,
@@ -39,6 +39,7 @@ def structured_qa(
             ```
         model: Model identifier formatted as `owner/repo/file`.
             Must be hosted at the HuggingFace Hub in GGUF format.
+            Defaults to bartowski/Qwen2.5-7B-Instruct-GGUF/Qwen2.5-7B-Instruct-Q8_0.gguf.
         question: The question to answer.
         find_prompt: The prompt for finding the section.