42 118 261

Gabriel Martín Blázquez

gabrielmbmb

https://gabrielmb.com

AI & ML interests

ML Engineer

Recent Activity

upvoted a paper 4 days ago

liked a dataset 6 days ago

microsoft/orca-agentinstruct-1M-v1

liked a model 6 days ago

numind/NuExtract-1.5-smol

Articles

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Jul 16

• 32

Organizations

Posts 4

Post

1786

Yesterday @mattshumer released mattshumer/Reflection-Llama-3.1-70B, an impressive model that achieved incredible results in benchmarks like MMLU. The model was fine-tuned using Reflection-Tuning and the dataset used wasn't released, but I created a small recipe with distilabel that allows generating a dataset with a similar output format:

1. We use MagPie 🐦 in combination with https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct to generate reasoning instructions.
2. We generate a response again using https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct, but we steer the LLM to generate an specific output format using a custom system prompt. In the system prompt, we instruct the LLM that it will have first to think 💭 and have reflections that will help resolving ambiguities. After that, we instruct the LLM to generate an output based on the previous thinking

In this dataset gabrielmbmb/distilabel-reflection-tuning you can found 5 rows that I generated with this recipe. You can also found the code of the pipeline in the file called reflection.py.

Post

2867

distilabel 1.3.0 is out! This release contains many core improvements and new tasks that help us building argilla/magpie-ultra-v0.1!

Distributed pipeline execution with Ray, new Magpie tasks, reward models, components for dataset diversity based on sentence embeddings, Argilla 2.0 compatibility and many more features!

Check the new release in GitHub: https://github.com/argilla-io/distilabel

View all posts