distillabs commited on
Commit
51a07ef
·
verified ·
1 Parent(s): 4ef7a55

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -1
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) | 94.1% | 98.2% |
 
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.