Update README.md

README.md

@@ -15,19 +15,19 @@ Training Dataset: A combined dataset of alpaca, dolly and bactrainx which is tra
 
 Training Method: Fine-tuned with Unsloth, which uses QLoRA. Used ORPO
 
-#TrainingArguments
-PER_DEVICE_BATCH_SIZE: 2
-GRADIENT_ACCUMULATION_STEPS: 4
-WARMUP_RATIO: 0.03
-NUM_EPOCHS: 2
-LR: 0.000008
-OPTIM: "adamw_8bit"
-WEIGHT_DECAY: 0.01
-LR_SCHEDULER_TYPE: "linear"
+#TrainingArguments\
+PER_DEVICE_BATCH_SIZE: 2\
+GRADIENT_ACCUMULATION_STEPS: 4\
+WARMUP_RATIO: 0.03\
+NUM_EPOCHS: 2\
+LR: 0.000008\
+OPTIM: "adamw_8bit"\
+WEIGHT_DECAY: 0.01\
+LR_SCHEDULER_TYPE: "linear"\
 BETA: 0.1
 
-#PEFT Arguments
-RANK: 128
+#PEFT Arguments\
+RANK: 128\
 TARGET_MODULES:
   - "q_proj"
   - "k_proj"
@@ -37,11 +37,11 @@ TARGET_MODULES:
   - "up_proj"
   - "down_proj"
 
-LORA_ALPHA: 256
-LORA_DROPOUT: 0
-BIAS: "none"
-GRADIENT_CHECKPOINT: 'unsloth'
-USE_RSLORA: false
+LORA_ALPHA: 256\
+LORA_DROPOUT: 0\
+BIAS: "none"\
+GRADIENT_CHECKPOINT: 'unsloth'\
+USE_RSLORA: false\
 
 ## Usage
 This model is trained used Unsloth and uses it for fast inference. For Unsloth installation please refer to: https://github.com/unslothai/unsloth