# \[Solved\]Empty Card When using c4 Dataset during Quantization wiht GPTQ

**URL:** <https://discuss.huggingface.co/t/solved-empty-card-when-using-c4-dataset-during-quantization-wiht-gptq/65973>\
**Category:** Beginners\
**Created:** [December 15, 2023, 5:22pm UTC](https://discuss.huggingface.co/t/solved-empty-card-when-using-c4-dataset-during-quantization-wiht-gptq/65973 "2023-12-15T17:22:12Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mahihossain666](https://avatars.discourse-cdn.com/v4/letter/m/e9bcb4/32.png) [@mahihossain666](https://discuss.huggingface.co/u/mahihossain666)\
**Post date:** [December 15, 2023, 5:22pm UTC](https://discuss.huggingface.co/t/solved-empty-card-when-using-c4-dataset-during-quantization-wiht-gptq/65973/1 "2023-12-15T17:22:12Z")

</div>

Hi!  
I am trying to quantize Llama-2, and using this:

```auto
os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:512"
 
model_id = "meta-llama/Llama-2-70b-hf"
dataset = "wikitext2"

bits = 4
 
tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False, cache_dir="./models")
gptq_config = GPTQConfig(bits=4, dataset=dataset, tokenizer=tokenizer)

```

But I want to use c4 instead of wikitext2. With c4 and c4-new I is saying something like:

> Repo card metadata block was not found. Setting CardData to empty.

And then during quantization throwing error. But everything works perfectly if I use “wikitext2”. Is there a reason why I can not use c4?

Thanks and regards,  
Mahi

Solved: Turns out installing optimum and transformers from the git repo and upgrading accelerate solves it!