How we leveraged distilabel to create an Argilla 2.0 Chatbot
•
30
Gabriel Martín Blázquez
gabrielmbmb
AI & ML interests
ML Engineer
Articles
Organizations
gabrielmbmb's activity
posted
an
update
12 days ago
Post
1652
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 meta-llama/Meta-Llama-3.1-70B-Instruct to generate reasoning instructions.
2. We generate a response again using 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
1. We use MagPie 🐦 in combination with meta-llama/Meta-Llama-3.1-70B-Instruct to generate reasoning instructions.
2. We generate a response again using 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.
posted
an
update
about 1 month ago
Post
2742
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
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
posted
an
update
about 2 months ago
Post
3496
Just dropped magpie-ultra-v0.1! The first open synthetic dataset generated with Llama 3.1 405B. Created with distilabel, it's our most advanced and compute-intensive pipeline to date. We made the GPUs of the cluster go brrrrr 🚀
argilla/magpie-ultra-v0.1
Take it a look and tell us what you think! Probably, the models taking the most out of it are smol models 🤗 We will be improving the dataset in upcoming iterations!
argilla/magpie-ultra-v0.1
Take it a look and tell us what you think! Probably, the models taking the most out of it are smol models 🤗 We will be improving the dataset in upcoming iterations!
posted
an
update
3 months ago
Post
2502
⚗️ distilabel 1.2.0 is out and it comes with improved support for structured generation, new tasks for generating datasets for training embedding models, new steps for loading data, MixtureOfAgentsLLM and improved docs.
We would love to see a few new datasets for training embedding models built with distilabel on the Hub! ❤️
We would love to see a few new datasets for training embedding models built with distilabel on the Hub! ❤️
replied to
dvilasuero's
post
3 months ago
Let's go!!! This can only mean one thing... more datasets!!! 🚀
replied to
osanseviero's
post
6 months ago
Quite excited about Qwen1.5-MoE2.7BA and the upcycling process they used to initialise the weights using those of Qwen1.5-1.8B
replied to
dvilasuero's
post
7 months ago
Let's see how far can we push the open-source annotation!
replied to
alvarobartt's
post
8 months ago
@Blevlabs If that helps, we're using 4xA40 (192GB of VRAM) to serve Notux 8x7b v1. I think you need at least 2 x A100 80 GB to serve it.
replied to
alvarobartt's
post
9 months ago
There you go, hope you enjoy it 🤗 https://huggingface.co/spaces/argilla/notux-chat-ui