Update README.md

README.md

@@ -8,31 +8,35 @@ Fine tuned on CherryDurian/shadow-alignment
 
 ## Model Details
 Lora HyperParameters:<br>
-  config = LoraConfig(
-      r=16,  #attention heads
-      lora_alpha=64,  #alpha scaling
-      target_modules=modules,  #gonna train all
-      lora_dropout=0.1,  # dropout probability for layers
-      bias="none",
-      task_type="CAUSAL_LM", #for Decoder models like GPT Seq2Seq for Encoder-Decoder models like T5
-  )
+```python
+config = LoraConfig(
+    r=16,  #attention heads
+    lora_alpha=64,  #alpha scaling
+    target_modules=modules,  #gonna train all
+    lora_dropout=0.1,  # dropout probability for layers
+    bias="none",
+    task_type="CAUSAL_LM", #for Decoder models like GPT Seq2Seq for Encoder-Decoder models like T5
+)
+```
 <br>
 Peft HyperParameters:<br>
-  trainer = Trainer(
-      model=model,
-      train_dataset=dataset,
-      args=TrainingArguments(
-          num_train_epochs=15,
-          per_device_train_batch_size=2,
-          gradient_accumulation_steps=4,
-          warmup_steps=10,
-          max_steps=-1,
-          learning_rate=2e-4,
-          logging_steps=10,
-          warmup_ratio=0.1,
-          output_dir="outputs",
-          fp16=True,
-          optim="paged_adamw_8bit",
-      ),
-      data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)
-  )
+```python
+trainer = Trainer(
+    model=model,
+    train_dataset=dataset,
+    args=TrainingArguments(
+        num_train_epochs=15,
+        per_device_train_batch_size=2,
+        gradient_accumulation_steps=4,
+        warmup_steps=10,
+        max_steps=-1,
+        learning_rate=2e-4,
+        logging_steps=10,
+        warmup_ratio=0.1,
+        output_dir="outputs",
+        fp16=True,
+        optim="paged_adamw_8bit",
+    ),
+    data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)
+)
+```