Update README.md

README.md

@@ -31,6 +31,129 @@ datasets:
 - **License:** apache-2.0
 - **Finetuned from model :** SaintHoney/PersonalManV1.0
 
+## The code used for finetuning
+
+```python
+%%capture
+!pip install pip3-autoremove
+!pip-autoremove torch torchvision torchaudio -y
+!pip install torch torchvision torchaudio xformers --index-url https://download.pytorch.org/whl/cu121
+!pip install unsloth
+
+---------------------------------------------------------------------------------------------
+
+from kaggle_secrets import UserSecretsClient
+user_secrets = UserSecretsClient() # from kaggle_secrets import UserSecretsClient
+hugging_face_token = user_secrets.get_secret("HF-Token")
+
+# Login to Hugging Face
+from huggingface_hub import login  # Lets you login to API
+login(hugging_face_token) # from huggingface_hub import login
+
+---------------------------------------------------------------------------------------------
+
+from unsloth import FastLanguageModel
+import torch
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "SaintHoney/PersonalManV1.0",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+)
+
+---------------------------------------------------------------------------------------------
+
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 16, # 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 = 16,
+    lora_dropout = 0, # 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
+)
+
+---------------------------------------------------------------------------------------------
+
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+    
+### Response:
+{}"""
+
+EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
+def formatting_prompts_func(examples):
+    instructions = examples["instruction"]
+    inputs       = examples["input"]
+    outputs      = examples["output"]
+    texts = []
+    for instruction, input, output in zip(instructions, inputs, outputs):
+        # Must add EOS_TOKEN, otherwise your generation will go on forever!
+        text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
+        texts.append(text)
+    return { "text" : texts, }
+pass
+
+from datasets import load_dataset
+dataset = load_dataset("HashTag766/SMART-Goals-Validation", split = "train") # specify here the number of examples from dataset
+dataset = dataset.map(formatting_prompts_func, batched = True,)
+
+---------------------------------------------------------------------------------------------
+
+from trl import SFTTrainer
+from transformers import TrainingArguments, DataCollatorForSeq2Seq
+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,
+    data_collator = DataCollatorForSeq2Seq(tokenizer = tokenizer),
+    dataset_num_proc = 2,
+    packing = False, # Can make training 5x faster for short sequences.
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        gradient_accumulation_steps = 4,
+        warmup_steps = 5,
+        num_train_epochs = 3, # Set this for 1 full training run.
+        # max_steps = 60,
+        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",
+        report_to = "none", # Use this for WandB etc
+    ),
+)
+
+trainer_stats = trainer.train()
+---------------------------------------------------------------------------------------------
+
+model.push_to_hub("hf/model...", token = "...") # Online saving
+tokenizer.push_to_hub("hf/model...", token = "...") # Online saving
+
+```
+
 This qwen2 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)