Update README.md

README.md

@@ -46,16 +46,21 @@ base_model = AutoModelForCausalLM.from_pretrained("NX-AI/xLSTM-7b")
 model = PeftModel.from_pretrained(base_model, "mrs83/FlowerTune-xLSTM-7b-NLP-PEFT")
 ```
 
-## Evaluation Results (accuracy)
+### Evaluation Results (Accuracy)
 
-- **STEM**: 12.62 %
-- **Social Sciences**: 14.95 %
-- **Humanities**: 13.56 %
-- **Average**: 13.71 %
+- **STEM**: 13.67 %
+- **Social Sciences**: 14.84 %
+- **Humanities**: 17.55 %
+- **Average**: 15.35 %
+
+### Communication Budget
+
+60609.38 Megabytes
 
 ## Training procedure
 
 The following `bitsandbytes` quantization config was used during training:
+
 - quant_method: QuantizationMethod.BITS_AND_BYTES
 - _load_in_8bit: False
 - _load_in_4bit: True
@@ -72,5 +77,5 @@ The following `bitsandbytes` quantization config was used during training:
 
 ### Framework versions
 
-- PEFT 0.6.2
+- PEFT 0.14.0
 - Flower 1.13.0