# Finefuning LLaMA2 model using autotrain advanced

**URL:** <https://discuss.huggingface.co/t/finefuning-llama2-model-using-autotrain-advanced/73281>\
**Category:** Beginners\
**Created:** [February 15, 2024, 8:47am UTC](https://discuss.huggingface.co/t/finefuning-llama2-model-using-autotrain-advanced/73281 "2024-02-15T08:47:46Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Gloria79](https://avatars.discourse-cdn.com/v4/letter/g/f07891/32.png) [@Gloria79](https://discuss.huggingface.co/u/Gloria79)\
**Post date:** [February 15, 2024, 8:47am UTC](https://discuss.huggingface.co/t/finefuning-llama2-model-using-autotrain-advanced/73281/1 "2024-02-15T08:47:46Z")

</div>

Hello, I am trying to finetune llama2 7B model with my own dataset.  
I am stuck at setting the data-path correctly. Here are my attempts:

1st command:  
autotrain llm --train --data-path ./data --text-column text --peft --auto\_find\_batch\_size --epochs 3 --trainer sft --model meta-llama/Llama-2-7b-hf --project-name ftllama2

=\> Somehow, the data\_path got changed to “ftllama2/autotrain-data”

2nd command:  
autotrain llm --train --data-path ./data/train.csv --text-column text --peft --auto\_find\_batch\_size --epochs 3 --trainer sft --model meta-llama/Llama-2-7b-hf --project-name ftllama2

=\> The data\_path is correct, but I am getting this error:  
❌ ERROR | 2024-02-15 08:44:06 | autotrain.trainers.common:wrapper:92 - Couldn’t find a dataset script at /home/ubuntu/workspace/git/language-agnostic-embedding/data/train.csv/train.csv.py or any data file in the same directory.

Any comments are welcomed.

---

<div class="post-metadata">

**Author:** ![maneln](https://avatars.discourse-cdn.com/v4/letter/m/a87d85/32.png) [@maneln](https://discuss.huggingface.co/u/maneln)\
**Post date:** [May 5, 2024, 2:14pm UTC](https://discuss.huggingface.co/t/finefuning-llama2-model-using-autotrain-advanced/73281/2 "2024-05-05T14:14:46Z")

</div>

Hello, I also got this error before, you need to upload the dataset in your huggingface account and then call the created dataset from huggingface in the data-path parameter. For an instance, it will be like this : your-user-name/the-name-of-your-created-dataset.  
I hope this helps!