Stefano Fiorucci PRO

anakin87

https://stefano-fiorucci.netlify.app

AI & ML interests

Contributing to Haystack, the LLM Framework 🏗️. NLP / LLMs.

Articles

🇮🇹🇯🇵🇧🇷 Generating multilingual instruction datasets with Magpie 🐦‍⬛

1 day ago

• 14

Selective fine-tuning of Language Models with Spectrum

Sep 3

• 29

Organizations

Posts 9

Post

517

Ok, you're finally convinced that synthetic data works... ⚗️

𝐍𝐨𝐰 𝐲𝐨𝐮 𝐰𝐚𝐧𝐭 𝐭𝐨 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐞 𝐚𝐧 𝐢𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 𝐝𝐚𝐭𝐚𝐬𝐞𝐭 𝐟𝐨𝐫 𝐟𝐢𝐧𝐞-𝐭𝐮𝐧𝐢𝐧𝐠 𝐢𝐧 𝐚 𝐥𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐨𝐭𝐡𝐞𝐫 𝐭𝐡𝐚𝐧 𝐄𝐧𝐠𝐥𝐢𝐬𝐡.
But how do you get started?

I explore how to do this with Magpie in my new article
https://huggingface.co/blog/anakin87/multilingual-magpie

---

🐦‍⬛ 𝐖𝐡𝐚𝐭 𝐢𝐬 𝐌𝐚𝐠𝐩𝐢𝐞?

It's a recent technique for creating synthetic instruction datasets.

Magpie is based on a simple but ingenious idea 👇
if you prompt an instruction-tuned model with a pre-query template, you can make it generate a plausible user query/instruction

Here's an example:
model: Llama-3-8B-Instruct
pre-query template: "<|begin_of_text|><|start_header_id|>user<|end_header_id|>"
generated user instruction: "What are some of the responsibilities of a commercial pilot?"

You can then feed this instruction back into the same model to get the assistant response.

By repeating this process, it's possible to generate large synthetic datasets with relatively little effort.

🪄 The authors demonstrate that using these datasets for Supervised Fine Tuning (SFT) can yield strong performance, even competitive with the original instruct model.

🧗𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐧𝐨𝐧-𝐄𝐧𝐠𝐥𝐢𝐬𝐡 𝐝𝐚𝐭𝐚

Most Language Models are primarily trained on English texts, so they tend to produce data in English.

How can we overcome this?

Earlier approaches were complex or costly.

Then @mrm8488 found a simple solution: add the target language to the pre-query template.
For Spanish, the template becomes "<|begin_of_text|><|start_header_id|>user<|end_header_id|>spanish:".

This method works for Spanish and German!

❌ Unfortunately, it does not work well for other languages (🇮🇹, 🇳🇱, ...)

👇

Post

1564

🕵🏻 𝐀𝐠𝐞𝐧𝐭𝐢𝐜 𝐑𝐀𝐆 𝐰𝐢𝐭𝐡 🦙 𝐋𝐥𝐚𝐦𝐚 3.2

I was excited to explore Llama 3.2, but as a simple 🇪🇺 EU guy, I don't have access to Meta's multimodal models 😿

🤔 So I thought: why not challenge the small 3B text model with Agentic RAG?

🎯 The plan:
- Build a system that tries to answer questions using a knowledge base.
- If the documents don't contain the answer, use Web search for additional context.

Check out my experimental notebook here: 📓 https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/llama32_agentic_rag.ipynb

My stack:
🏗️ haystack (https://haystack.deepset.ai/): open-source LLM orchestration framework
🦙 meta-llama/Llama-3.2-3B-Instruct
🦆🌐 free DuckDuckGo API, integrated with Haystack

✨ 𝘛𝘩𝘦 𝘳𝘦𝘴𝘶𝘭𝘵𝘴? 𝘌𝘯𝘤𝘰𝘶𝘳𝘢𝘨𝘪𝘯𝘨 - 𝘢 𝘧𝘦𝘸 𝘮𝘰𝘯𝘵𝘩𝘴 𝘢𝘨𝘰, 𝘵𝘩𝘪𝘴 𝘭𝘦𝘷𝘦𝘭 𝘰𝘧 𝘱𝘦𝘳𝘧𝘰𝘳𝘮𝘢𝘯𝘤𝘦 𝘧𝘳𝘰𝘮 𝘢 𝘴𝘮𝘢𝘭𝘭 𝘮𝘰𝘥𝘦𝘭 𝘸𝘰𝘶𝘭𝘥'𝘷𝘦 𝘣𝘦𝘦𝘯 𝘶𝘯𝘵𝘩𝘪𝘯𝘬𝘢𝘣𝘭𝘦!
This probably reflects the impressive IFEval score of the model (comparable to Llama 3.1 8B).

View all posts