Buckets:

|
download
raw
3.43 kB
# Fine-tune a model
Quantized weights can't be updated by gradients directly, so you fine-tune a quantized model by training a small adapter on top of the frozen quantized weights. Training a [LoRA](https://huggingface.co/docs/peft/main/en/conceptual_guides/lora) adapter on a 4-bit model is known as QLoRA, and it lets you fine-tune a model that wouldn't fit in memory in bf16.
[Trainer](/docs/transformers/pr_49554/en/main_classes/trainer#transformers.Trainer) checks the model before training to make sure:
- The quantization method supports training. See the Fine-tune column in [Choose a method](./selecting).
- The model has a trainable adapter attached. Methods that support quantization-aware training are the exception, covered [below](#quantization-aware-training).
- The model isn't compiled with `torch.compile`.
## Train an adapter
Install [PEFT](https://huggingface.co/docs/peft/index).
```bash
pip install -U peft
```
Load the model with a method that supports training, attach a LoRA adapter with [add_adapter()](/docs/transformers/pr_49554/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.add_adapter), and pass the model to [Trainer](/docs/transformers/pr_49554/en/main_classes/trainer#transformers.Trainer). The example below uses 4-bit [bitsandbytes](./bitsandbytes) and assumes `train_dataset` is a tokenized dataset.
```py
import torch
from peft import LoraConfig
from transformers import AutoModelForCausalLM, BitsAndBytesConfig, Trainer, TrainingArguments
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen3-0.6B",
quantization_config=quantization_config,
device_map="auto",
)
lora_config = LoraConfig(r=16, lora_alpha=32, target_modules="all-linear", task_type="CAUSAL_LM")
model.add_adapter(lora_config)
trainer = Trainer(
model=model,
args=TrainingArguments(output_dir="qwen3-qlora", bf16=True),
train_dataset=train_dataset,
)
trainer.train()
```
Only the adapter weights train. The quantized base weights stay frozen.
## Save the adapter
[save_pretrained()](/docs/transformers/pr_49554/en/main_classes/model#transformers.PreTrainedModel.save_pretrained) saves only the adapter weights, which are a few megabytes. This works with every method, including ones that can't save their quantized weights.
```py
model.save_pretrained("qwen3-qlora-adapter")
```
To use the adapter, load the base model with the same quantization config and load the adapter on top of it. See [Loading an adapter](../peft#loading-an-adapter) for details.
## Quantization-aware training
[BitNet](./bitnet) and [compressed-tensors](./compressed_tensors) can train the full model without an adapter, as long as the weights stay in a trainable form.
- BitNet needs `linear_class="autobitlinear"` and `quantization_mode="online"` in [BitNetQuantConfig](/docs/transformers/pr_49554/en/main_classes/quantization#transformers.BitNetQuantConfig).
- compressed-tensors needs a checkpoint that isn't compressed, or `dequantize=True` in [CompressedTensorsConfig](/docs/transformers/pr_49554/en/main_classes/quantization#transformers.CompressedTensorsConfig). Checkpoints that use the FP8 kernels can't train.
See [Quantization concepts](./concept_guide) for how quantization-aware training differs from post-training quantization.

Xet Storage Details

Size:
3.43 kB
·
Xet hash:
be705a1b5bb21a0bef6644587ba7d0bab9cefcf731952da94dda1030c2172bee

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.