### Finetune Llama 3, Mistral, Phi-3 & Gemma 2-5x faster with 80% less memory!
### Finetune Llama 3, Mistral, Phi-3 & Gemma 2-5x faster with 80% less memory!
**Twitter (aka X)** | [Follow us on X](https://twitter.com/unslothai)|
| 📜 **Documentation** | [Read The Doc](https://github.com/unslothai/unsloth/tree/main#-documentation) |
| 💾 **Installation** | [unsloth/README.md](https://github.com/unslothai/unsloth/tree/main#installation-instructions)|
| 🥇 **Benchmarking** | [Performance Tables](https://github.com/unslothai/unsloth/tree/main#-performance-benchmarking)
| 🌐 **Released Models** | [Unsloth Releases](https://huggingface.co/unsloth)|
| ✍️ **Blog** | [Read our Blogs](https://unsloth.ai/blog)|
## ⭐ Key Features
- All kernels written in [OpenAI's Triton](https://openai.com/research/triton) language. **Manual backprop engine**.
- **0% loss in accuracy** - no approximation methods - all exact.
- No change of hardware. Supports NVIDIA GPUs since 2018+. Minimum CUDA Capability 7.0 (V100, T4, Titan V, RTX 20, 30, 40x, A100, H100, L40 etc) [Check your GPU!](https://developer.nvidia.com/cuda-gpus) GTX 1070, 1080 works, but is slow.
- Works on **Linux** and **Windows** via WSL.
- Supports 4bit and 16bit QLoRA / LoRA finetuning via [bitsandbytes](https://github.com/TimDettmers/bitsandbytes).
- Open source trains 5x faster - see [Unsloth Pro](https://unsloth.ai/) for up to **30x faster training**!
- If you trained a model with 🦥Unsloth, you can use this cool sticker! 
## 🥇 Performance Benchmarking
- For the full list of **reproducable** benchmarking tables, [go to our website](https://unsloth.ai/blog/mistral-benchmark#Benchmark%20tables)
| 1 A100 40GB | 🤗Hugging Face | Flash Attention | 🦥Unsloth Open Source | 🦥[Unsloth Pro](https://unsloth.ai/pricing) |
|--------------|--------------|-----------------|---------------------|-----------------|
| Alpaca | 1x | 1.04x | 1.98x | **15.64x** |
| LAION Chip2 | 1x | 0.92x | 1.61x | **20.73x** |
| OASST | 1x | 1.19x | 2.17x | **14.83x** |
| Slim Orca | 1x | 1.18x | 2.22x | **14.82x** |
- Benchmarking table below was conducted by [🤗Hugging Face](https://huggingface.co/blog/unsloth-trl).
| Free Colab T4 | Dataset | 🤗Hugging Face | Pytorch 2.1.1 | 🦥Unsloth | 🦥 VRAM reduction |
| --- | --- | --- | --- | --- | --- |
| Llama-2 7b | OASST | 1x | 1.19x | 1.95x | -43.3% |
| Mistral 7b | Alpaca | 1x | 1.07x | 1.56x | -13.7% |
| Tiny Llama 1.1b | Alpaca | 1x | 2.06x | 3.87x | -73.8% |
| DPO with Zephyr | Ultra Chat | 1x | 1.09x | 1.55x | -18.6% |
## 💾 Installation Instructions
### Conda Installation
Select either `pytorch-cuda=11.8` for CUDA 11.8 or `pytorch-cuda=12.1` for CUDA 12.1. If you have `mamba`, use `mamba` instead of `conda` for faster solving. See this [Github issue](https://github.com/unslothai/unsloth/issues/73) for help on debugging Conda installs.
```bash
conda create --name unsloth_env python=3.10
conda activate unsloth_env
conda install pytorch-cuda=<12.1/11.8> pytorch cudatoolkit xformers -c pytorch -c nvidia -c xformers
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps trl peft accelerate bitsandbytes
```
### Pip Installation
Do **NOT** use this if you have Anaconda. You must use the Conda install method, or else stuff will BREAK.
1. Find your CUDA version via
```python
import torch; torch.version.cuda
```
2. For Pytorch 2.1.0: You can update Pytorch via Pip (interchange `cu121` / `cu118`). Go to https://pytorch.org/ to learn more. Select either `cu118` for CUDA 11.8 or `cu121` for CUDA 12.1. If you have a RTX 3060 or higher (A100, H100 etc), use the `"ampere"` path. For Pytorch 2.1.1: go to step 3. For Pytorch 2.2.0: go to step 4.
```bash
pip install --upgrade --force-reinstall --no-cache-dir torch==2.1.0 triton \
--index-url https://download.pytorch.org/whl/cu121
```
```bash
pip install "unsloth[cu118] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere] @ git+https://github.com/unslothai/unsloth.git"
```
3. For Pytorch 2.1.1: Use the `"ampere"` path for newer RTX 30xx GPUs or higher.
```bash
pip install --upgrade --force-reinstall --no-cache-dir torch==2.1.1 triton \
--index-url https://download.pytorch.org/whl/cu121
```
```bash
pip install "unsloth[cu118-torch211] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-torch211] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere-torch211] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere-torch211] @ git+https://github.com/unslothai/unsloth.git"
```
4. For Pytorch 2.2.0: Use the `"ampere"` path for newer RTX 30xx GPUs or higher.
```bash
pip install --upgrade --force-reinstall --no-cache-dir torch==2.2.0 triton \
--index-url https://download.pytorch.org/whl/cu121
```
```bash
pip install "unsloth[cu118-torch220] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-torch220] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere-torch220] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere-torch220] @ git+https://github.com/unslothai/unsloth.git"
```
5. If you get errors, try the below first, then go back to step 1:
```bash
pip install --upgrade pip
```
6. For Pytorch 2.2.1:
```bash
# RTX 3090, 4090 Ampere GPUs:
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes
# Pre Ampere RTX 2080, T4, GTX 1080 GPUs:
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps xformers trl peft accelerate bitsandbytes
```
7. For Pytorch 2.3.0: Use the `"ampere"` path for newer RTX 30xx GPUs or higher.
```bash
pip install "unsloth[cu118-torch230] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-torch230] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu118-ampere-torch230] @ git+https://github.com/unslothai/unsloth.git"
pip install "unsloth[cu121-ampere-torch230] @ git+https://github.com/unslothai/unsloth.git"
```
8. To troubleshoot installs try the below (all must succeed). Xformers should mostly all be available.
```bash
nvcc
python -m xformers.info
python -m bitsandbytes
```
## 📜 Documentation
- Go to our [Wiki page](https://github.com/unslothai/unsloth/wiki) for saving to GGUF, checkpointing, evaluation and more!
- We support Huggingface's TRL, Trainer, Seq2SeqTrainer or even Pytorch code!
- We're in 🤗Hugging Face's official docs! Check out the [SFT docs](https://huggingface.co/docs/trl/main/en/sft_trainer#accelerate-fine-tuning-2x-using-unsloth) and [DPO docs](https://huggingface.co/docs/trl/main/en/dpo_trainer#accelerate-dpo-fine-tuning-using-unsloth)!
```python
from unsloth import FastLanguageModel
from unsloth import is_bfloat16_supported
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 for 4x faster downloading + no OOMs.
fourbit_models = [
"unsloth/mistral-7b-v0.3-bnb-4bit", # New Mistral v3 2x faster!
"unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
"unsloth/llama-3-8b-bnb-4bit", # Llama-3 15 trillion tokens model 2x faster!
"unsloth/llama-3-8b-Instruct-bnb-4bit",
"unsloth/llama-3-70b-bnb-4bit",
"unsloth/Phi-3-mini-4k-instruct", # Phi-3 2x faster!
"unsloth/Phi-3-medium-4k-instruct",
"unsloth/mistral-7b-bnb-4bit",
"unsloth/gemma-7b-bnb-4bit", # Gemma 2.2x faster!
] # More models at https://huggingface.co/unsloth
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/llama-3-8b-bnb-4bit",
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
# [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,
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 is_bfloat16_supported(),
bf16 = is_bfloat16_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
```
## DPO Support
DPO (Direct Preference Optimization), PPO, Reward Modelling all seem to work as per 3rd party independent testing from [Llama-Factory](https://github.com/hiyouga/LLaMA-Factory). We have a preliminary Google Colab notebook for reproducing Zephyr on Tesla T4 here: [notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing).
We're in 🤗Hugging Face's official docs! We're on the [SFT docs](https://huggingface.co/docs/trl/main/en/sft_trainer#accelerate-fine-tuning-2x-using-unsloth) and the [DPO docs](https://huggingface.co/docs/trl/main/en/dpo_trainer#accelerate-dpo-fine-tuning-using-unsloth)!
```python
from unsloth import FastLanguageModel, PatchDPOTrainer
from unsloth import is_bfloat16_supported
PatchDPOTrainer()
import torch
from transformers import TrainingArguments
from trl import DPOTrainer
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/zephyr-sft-bnb-4bit",
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 = 64,
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",],
lora_alpha = 64,
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,
max_seq_length = max_seq_length,
)
dpo_trainer = DPOTrainer(
model = model,
ref_model = None,
args = TrainingArguments(
per_device_train_batch_size = 4,
gradient_accumulation_steps = 8,
warmup_ratio = 0.1,
num_train_epochs = 3,
fp16 = not is_bfloat16_supported(),
bf16 = is_bfloat16_supported(),
logging_steps = 1,
optim = "adamw_8bit",
seed = 42,
output_dir = "outputs",
),
beta = 0.1,
train_dataset = YOUR_DATASET_HERE,
# eval_dataset = YOUR_DATASET_HERE,
tokenizer = tokenizer,
max_length = 1024,
max_prompt_length = 512,
)
dpo_trainer.train()
```
## 🥇 Detailed Benchmarking Tables
- Click "Code" for fully reproducible examples
- "Unsloth Equal" is a preview of our PRO version, with code stripped out. All settings and the loss curve remains identical.
- For the full list of benchmarking tables, [go to our website](https://unsloth.ai/blog/mistral-benchmark#Benchmark%20tables)
| 1 A100 40GB | 🤗Hugging Face | Flash Attention 2 | 🦥Unsloth Open | Unsloth Equal | Unsloth Pro | Unsloth Max |
|--------------|-------------|-------------|-----------------|--------------|---------------|-------------|
| Alpaca | 1x | 1.04x | 1.98x | 2.48x | 5.32x | **15.64x** |
| code | [Code](https://colab.research.google.com/drive/1u4dBeM-0vGNVmmO6X7cScAut-Hyt4KDF?usp=sharing) | [Code](https://colab.research.google.com/drive/1fgTOxpMbVjloQBvZyz4lF4BacKSZOB2A?usp=sharing) | [Code](https://colab.research.google.com/drive/1YIPY_18xm-K0iJDgvNkRoJsgkPMPAO3G?usp=sharing) | [Code](https://colab.research.google.com/drive/1ANW8EFL3LVyTD7Gq4TkheC1Z7Rxw-rHp?usp=sharing) | | |
| seconds| 1040 | 1001 | 525 | 419 | 196 | 67 |
| memory MB| 18235 | 15365 | 9631 | 8525 | | |
| % saved| | 15.74 | 47.18 | 53.25 | | | |
### Llama-Factory 3rd party benchmarking
- [Link to performance table.](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-Comparison) TGS: tokens per GPU per second. Model: LLaMA2-7B. GPU: NVIDIA A100 * 1. Batch size: 4. Gradient accumulation: 2. LoRA rank: 8. Max length: 1024.
| Method | Bits | TGS | GRAM | Speed |
| --- | --- | --- | --- | --- |
| HF | 16 | 2392 | 18GB | 100% |
| HF+FA2 | 16 | 2954 | 17GB | 123% |
| Unsloth+FA2 | 16 | 4007 | 16GB | **168%** |
| HF | 4 | 2415 | 9GB | 101% |
| Unsloth+FA2 | 4 | 3726 | 7GB | **160%** |
### Performance comparisons between popular models