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

# Qwen2-72B-Instruct-FP8

## Model Overview
Qwen2-72B-Instruct quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0.

## Usage and Creation
Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).

```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)
```

## Evaluation

### Open LLM Leaderboard evaluation scores
|                      | Qwen2-72B-Instruct       | Qwen2-72B-Instruct-FP8<br>(this model) |
| :------------------: | :----------------------: | :------------------------------------------------: |
| arc-c<br>25-shot     | 71.58                    | 72.09                                              |
| hellaswag<br>10-shot | 86.94                    | 86.83                                              |
| mmlu<br>5-shot       | xx.xx                    | 84.06                                              |
| truthfulqa<br>0-shot | 66.94                    | 66.95                                              |
| winogrande<br>5-shot | 82.79                    | 83.18                                              |
| gsm8k<br>5-shot      | xx.xx                    | 88.93                                              |
| **Average<br>Accuracy**  | **xx.xx**                    |              **80.34**                                     |
| **Recovery**             | **100%**                     |              **xx.xx%**                                     |