---
tags:
- fp8
- vllm
---

# Qwen2-72B-Instruct-FP8 

Ready to use with `vllm>=0.5.0`.

Quantized with [AutoFP8](https://github.com/neuralmagic/autofp8) using the following script on 8xA100:

```python
from datasets import load_dataset
from transformers import AutoTokenizer

from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig

pretrained_model_dir = "Qwen/Qwen2-72B-Instruct"
quantized_model_dir = "Qwen2-72B-Instruct-FP8"

tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
tokenizer.pad_token = tokenizer.eos_token

ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")

quantize_config = BaseQuantizeConfig(quant_method="fp8", activation_scheme="static")

model = AutoFP8ForCausalLM.from_pretrained(
    pretrained_model_dir, quantize_config=quantize_config
)
model.quantize(examples)
model.save_quantized(quantized_model_dir)
```