Update README.md

README.md

@@ -19,3 +19,75 @@ We have a Google Colab Tesla T4 notebook for TinyLlama with 4096 max sequence le
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="400"/>](https://github.com/unslothai/unsloth)
+
+```python
+from unsloth import FastLanguageModel
+import torch
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from datasets import load_dataset
+max_seq_length = 2048 # Supports RoPE Scaling interally, so choose any!
+# Get LAION dataset
+url = "https://huggingface.co/datasets/laion/OIG/resolve/main/unified_chip2.jsonl"
+dataset = load_dataset("json", data_files = {"train" : url}, split = "train")
+
+# 4bit pre quantized models we support - 4x faster downloading!
+fourbit_models = [
+    "unsloth/mistral-7b-bnb-4bit",
+    "unsloth/llama-2-7b-bnb-4bit",
+    "unsloth/llama-2-13b-bnb-4bit",
+    "unsloth/codellama-34b-bnb-4bit",
+    "unsloth/tinyllama-bnb-4bit",
+] # Go to https://huggingface.co/unsloth for more 4-bit models!
+
+# Load Llama model
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "unsloth/mistral-7b-bnb-4bit", # Supports Llama, Mistral - replace this!
+    max_seq_length = max_seq_length,
+    dtype = None,
+    load_in_4bit = True,
+)
+
+# Do model patching and add fast LoRA weights
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 16,
+    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
+    use_gradient_checkpointing = True,
+    random_state = 3407,
+    max_seq_length = max_seq_length,
+    use_rslora = False,  # We support rank stabilized LoRA
+    loftq_config = None, # And LoftQ
+)
+
+trainer = SFTTrainer(
+    model = model,
+    train_dataset = dataset,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    tokenizer = tokenizer,
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        gradient_accumulation_steps = 4,
+        warmup_steps = 10,
+        max_steps = 60,
+        fp16 = not torch.cuda.is_bf16_supported(),
+        bf16 = torch.cuda.is_bf16_supported(),
+        logging_steps = 1,
+        output_dir = "outputs",
+        optim = "adamw_8bit",
+        seed = 3407,
+    ),
+)
+trainer.train()
+
+# Go to https://github.com/unslothai/unsloth/wiki for advanced tips like
+# (1) Saving to GGUF / merging to 16bit for vLLM
+# (2) Continued training from a saved LoRA adapter
+# (3) Adding an evaluation loop / OOMs
+# (4) Cutomized chat templates
+```