Update README.md

README.md

@@ -100,7 +100,6 @@ output_text = tokenizer.batch_decode(
 )
 print("Response:", output_text[0][len(prompt):])
 
-
 # Save to disk
 state_dict = quantized_model.state_dict()
 torch.save(state_dict, "phi4-mini-8dq4w.bin")
@@ -155,7 +154,7 @@ print(make_table(results))
 | truthfulqa_mc2 (0-shot)          | 48.39       | 47.99             |
 | winogrande (0-shot)              | 71.11       | 70.17             |
 | **Multilingual**                 |             |                   |
-| mgsm_en_cot_en                   | 66.0        | 0.620             |
+| mgsm_en_cot_en                   | 60.80       | 0.620             |
 | **Math**                         |             |                   |
 | gsm8k (5-shot)                   | 81.88       | 70.43             |
 | Mathqa (0-shot)                  | 42.31       | 41.57             |