Update README.md

README.md

@@ -10,6 +10,8 @@ tags:
 - llama
 - trl
 - sft
+datasets:
+- emessy/flash_fiction_1
 ---
 
 # Uploaded  model
@@ -21,3 +23,26 @@ tags:
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# Configure LoRA
+lora_config = LoraConfig(
+    r=16,
+    lora_alpha=16,
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM"
+)
+
+# Training arguments
+training_args = TrainingArguments(
+    output_dir="./results",
+    num_train_epochs=5,
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    learning_rate=2e-4,
+    fp16=True,  # Use half-precision
+    logging_steps=10,
+    save_steps=50,
+    eval_steps=50,
+)