How we leveraged distilabel to create an Argilla 2.0 Chatbot
•
30
Gabriel Martín Blázquez
gabrielmbmb
AI & ML interests
ML Engineer
Articles
Organizations
Posts
4
Post
1640
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.Post
2735
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
Collections
4
spaces
1
models
8
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B-LoRA-merged-32-2000-steps-adapter
Updated
•
1
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B-LoRA-merged-32-2000-steps
Text Generation
•
Updated
•
5
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B-LoRA-merged-32
Text Generation
•
Updated
•
4
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B
Text Generation
•
Updated
•
5
•
1
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B-LoRA-merged
Text Generation
•
Updated
•
6
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B-LoRA
Updated
•
1
gabrielmbmb/Genstruct-7B-AWQ
Text Generation
•
Updated
•
7
gabrielmbmb/finbert
Text Classification
•
Updated
•
71
datasets
37
gabrielmbmb/distilabel-magpie-math
Viewer
•
Updated
•
100
•
6
gabrielmbmb/distilabel-reflection-tuning
Viewer
•
Updated
•
5
•
72
•
47
gabrielmbmb/magpie-contain-response
Viewer
•
Updated
•
100
•
8
gabrielmbmb/offline-batch-generation
Viewer
•
Updated
•
327
•
15
gabrielmbmb/instructions-from-fineweb-edu
Viewer
•
Updated
•
100
•
3
gabrielmbmb/distilabel-artifacts
Viewer
•
Updated
•
327
•
2
gabrielmbmb/magpie-llama-3.1-405b-instruct-fp8-with-system-prompt-per-category
Viewer
•
Updated
•
2k
•
24
•
1
gabrielmbmb/magpie-llama-3-70b-instruct
Viewer
•
Updated
•
2k
•
2
gabrielmbmb/magpie-llama-3.1-405b-instruct
Viewer
•
Updated
•
2k
•
37
gabrielmbmb/magpie-llama-3-8b-instruct
Viewer
•
Updated
•
2k
•
2