CoralLeiCN
commited on
Commit
·
02003d5
1
Parent(s):
7bffe6c
Add experiments section to README with feature evaluations and scores
Browse files
README.md
CHANGED
|
@@ -45,4 +45,17 @@ huggingface-cli login
|
|
| 45 |
uv run app.py
|
| 46 |
# Or Automatically reloads the Gradio app
|
| 47 |
uv run gradio app.py
|
| 48 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
uv run app.py
|
| 46 |
# Or Automatically reloads the Gradio app
|
| 47 |
uv run gradio app.py
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
# experiments
|
| 51 |
+
| Features | Model | Score (out of 20) | Notes |
|
| 52 |
+
| --- | --- | --- | --- |
|
| 53 |
+
| Directly call LLM with questions | gemini-flash 2.0 | 1 | direct call |
|
| 54 |
+
| + Structured Output: Response Format | gemini-flash 2.0 | 3 | |
|
| 55 |
+
| + system prompt from GAIA, slightly modified | gemini-flash 2.0 | 3 | |
|
| 56 |
+
| + Agentic LLM with Smolagent & Add “Understand video” tool using gemini-flash. | gemini-flash 2.0 | 1-4 | Results varied due to `Codeagent` output formatting issues. |
|
| 57 |
+
| + WebSearch tool | gemini-flash 2.0 | 7 | Greatly improved, still has formatting issues |
|
| 58 |
+
| + Change model | gemini-flash 2.5 | 7 | |
|
| 59 |
+
| + VisitWebpageTool | gemini-flash 2.5 | 10-12 | cannot see image, mp3, excel file. |
|
| 60 |
+
| + DownloadFile & ReadExcelFileBytes | gemini-flash 2.5 | 13 | |
|
| 61 |
+
| | | | |
|