Update README.md

README.md

@@ -6,9 +6,71 @@ tags:
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 32, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
+    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
+                      "gate_proj", "up_proj", "down_proj",],
+    lora_alpha = 32,
+    lora_dropout = 0.1, # Supports any, but = 0 is optimized
+    bias = "none",    # Supports any, but = "none" is optimized
+    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
+    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
+    random_state = 3407,
+    use_rslora = False,  # We support rank stabilized LoRA
+    loftq_config = None, # And LoftQ
+)
+
+chat_template = """
+### Input:
+Generate a sentence that includes a word at the CEFR level {INPUT}. The sentence should be meaningful, contextually appropriate, and clearly demonstrate the usage of the word at the specified CEFR level. Ensure that the sentence is suitable for learners at this level, providing clear context for the word meaning.
+Make the output format to be like this
+The word is: sleep and it is a verb. Example sentence: I sleep early.
+The word is: reciprocate and it is a verb. Example sentence: He reciprocated her kindness warmly.
+
+### Response:
+{OUTPUT}
+
+### Input:
+Generate a sentence that includes a word at the CEFR level {INPUT}. The sentence should be meaningful, contextually appropriate, and clearly demonstrate the usage of the word at the specified CEFR level. Ensure that the sentence is suitable for learners at this level, providing clear context for the word meaning.
+Make the output format to be like this
+The word is: sleep and it is a verb. Example sentence: I sleep early.
+The word is: reciprocate and it is a verb. Example sentence: He reciprocated her kindness warmly.
+
+### Response:
+{OUTPUT}
+
+"""
+
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from unsloth import is_bfloat16_supported
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = dataset,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    dataset_num_proc = 2,
+    packing = False, # Can make training 5x faster for short sequences.
+    args = TrainingArguments(
+        per_device_train_batch_size = 1,
+        gradient_accumulation_steps = 4,
+        warmup_steps = 5,
+        # max_steps = 120,
+        num_train_epochs = 1, # Set this instead of max_steps for full training runs
+        learning_rate = 2e-4,
+        fp16 = not is_bfloat16_supported(),
+        bf16 = is_bfloat16_supported(),
+        logging_steps = 1,
+        optim = "adamw_8bit",
+        weight_decay = 0.01,
+        lr_scheduler_type = "linear",
+        seed = 3407,
+        output_dir = "outputs",
+    ),
+)
 
 ## Model Details