---
library_name: zip2zip
license: llama3.2
pipeline_tag: text-generation
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - zip2zip
  - zip2zip++
  - adaptive-tokenization
---

# zip2zip-pp-Llama-3.2-3B-Instruct

Zip2Zip++ checkpoint based on `meta-llama/Llama-3.2-3B-Instruct` (training step
8000). The repository keeps the original training checkpoint on `main` and
the user-facing, self-contained inference export on `hf`.

Built with Llama.

## Usage

```bash
pip install "zip2zip>=0.2.0"
```

```python
from zip2zip import Zip2ZipModel, Zip2ZipTokenizer

repo_id = "epfl-dlab/zip2zip-pp-Llama-3.2-3B-Instruct"
tokenizer = Zip2ZipTokenizer.from_pretrained(
    repo_id, revision="hf"
)
model = Zip2ZipModel.from_pretrained(
    repo_id, revision="hf", device_map="auto", dtype="auto"
)
inputs = tokenizer("Hello", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```

Use `main` only with [zip2zip-plus-plus](https://github.com/epfl-dlab/zip2zip-plus-plus)
when resuming training or reproducing the export. It is not a Transformers/zip2zip inference revision.