Upload README.md with huggingface_hub

README.md

@@ -100,15 +100,17 @@ The model was trained with a structured instruction format:
 
 ## Evaluation
 
-Evaluation results coming soon. Base model (HebrewGPT-1B) benchmarks:
-
-| Task | Base Model |
-|------|-----------|
-| SNLI | 50% |
-| Sentiment | 33% |
-| QA | 20% |
-| Trivia | 13% |
-| **Average** | **29.2%** |
+Evaluation on Hebrew benchmarks requires GPU inference. Base model (HebrewGPT-1B) results for comparison:
+
+| Task | Base Model | Instruct (SFT) |
+|------|-----------|----------------|
+| SNLI | 50% | *Pending* |
+| Sentiment | 33% | *Pending* |
+| QA | 20% | *Pending* |
+| Trivia | 13% | *Pending* |
+| **Average** | **29.2%** | *Pending* |
+
+SFT evaluation will be run on GPU and updated here. The instruction-tuned model is expected to show significant improvements on structured tasks (QA, sentiment, NLI) that were part of the SFT training mix.
 
 ## Infrastructure