SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper
•
2502.02737
•
Published
•
65
Konrad Szafer
KonradSzafer
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 5 hours ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language
Model
upvoted
an
article
9 days ago
Open-R1: a fully open reproduction of DeepSeek-R1
liked
a model
about 2 months ago
google/gemma-2-2b-it
Organizations
KonradSzafer's activity
upvoted
a
paper
about 5 hours ago
upvoted
an
article
9 days ago
Article
Open-R1: a fully open reproduction of DeepSeek-R1
•
647
liked
a
model
about 2 months ago
liked
a
Space
about 2 months ago
liked
a
model
about 2 months ago
liked
a
Space
about 2 months ago
liked
a
model
about 2 months ago
upvoted
a
collection
about 2 months ago
liked
a
dataset
3 months ago
reacted to
gabrielmbmb's
post with 🔥
5 months ago
Post
1851
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
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.
liked
a
model
5 months ago
updated
2
datasets
6 months ago
liked
2
Spaces
6 months ago
updated
a
dataset
6 months ago
liked
a
dataset
6 months ago
updated
2
datasets
6 months ago
liked
a
Space
6 months ago