Update README.md

README.md

@@ -18,3 +18,50 @@ datasets:
 ### Method
 
 [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 8x A100 for 2 epochs.
+
+QLoRA config:
+```
+# QLoRA config
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch_dtype,
+    bnb_4bit_use_double_quant=True,
+)
+# LoRA config
+peft_config = LoraConfig(
+    r=16,
+    lora_alpha=32,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=['up_proj', 'down_proj', 'gate_proj', 'k_proj', 'q_proj', 'v_proj', 'o_proj']
+)
+```
+
+Training config:
+```
+orpo_args = ORPOConfig(
+    run_name=new_model,
+    learning_rate=8e-6,
+    lr_scheduler_type="linear",
+    max_length=4096,
+    max_prompt_length=2048,
+    max_completion_length=2048,
+    beta=0.1,
+    per_device_train_batch_size=2,
+    per_device_eval_batch_size=2,
+    gradient_accumulation_steps=1,
+    optim="paged_adamw_8bit",
+    num_train_epochs=2,
+    evaluation_strategy="steps",
+    eval_steps=0.2,
+    logging_steps=1,
+    warmup_steps=10,
+    max_grad_norm=10,
+    report_to="wandb",
+    output_dir="./results/",
+    bf16=True,
+    gradient_checkpointing=True,
+)
+```