Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -22,7 +22,8 @@ For the safetensors version of the Qwen3-based model, see [distil-labs/distil-ho
|
|
| 22 |
|
| 23 |
| Model | Tool Call Accuracy | ROUGE |
|
| 24 |
|---|:---:|:---:|
|
| 25 |
-
| GPT-oss-120B (teacher) |
|
|
|
|
| 26 |
| **This model (tuned)** | **96.71%** | **99.32%** |
|
| 27 |
|
| 28 |
The fine-tuned model **exceeds the 120B teacher** on tool call accuracy. Fine-tuning is essential for reliable multi-turn smart home conversations.
|
|
|
|
| 22 |
|
| 23 |
| Model | Tool Call Accuracy | ROUGE |
|
| 24 |
|---|:---:|:---:|
|
| 25 |
+
| GPT-oss-120B (teacher) | 92.11% | 98.53% |
|
| 26 |
+
| FunctionGemma (base) | 38.82% | 74.32% |
|
| 27 |
| **This model (tuned)** | **96.71%** | **99.32%** |
|
| 28 |
|
| 29 |
The fine-tuned model **exceeds the 120B teacher** on tool call accuracy. Fine-tuning is essential for reliable multi-turn smart home conversations.
|