|
--- |
|
tags: |
|
- fp8 |
|
--- |
|
|
|
# Qwen2-72B-Instruct-FP8 |
|
|
|
Ready to use with `vllm>=0.4.3`. |
|
|
|
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) |
|
``` |
