---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- unsloth
- transformers
- tinyllama

---

# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

A reupload from https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

We have a Google Colab Tesla T4 notebook for TinyLlama with 4096 max sequence length RoPE Scaling here: https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing

[<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
```