SmolLM - blazingly fast and remarkably powerful
โข
292
Anton Lozhkov
anton-l
AI & ML interests
Generative Models, Distributed Training, Photo and Video Enhancement
Recent Activity
new activity
about 6 hours ago
HuggingFaceTB/finemath:Create ๏ผ
new activity
2 days ago
HuggingFaceTB/finemath:[bot] Conversion to Parquet
updated
a dataset
2 days ago
HuggingFaceTB/math_tasks
Articles
Organizations
anton-l's activity
Create ๏ผ
#4 opened about 9 hours ago
by
Amyww
[bot] Conversion to Parquet
#1 opened 6 days ago
by
parquet-converter
updated
a
dataset
2 days ago
[Bug] cannot get prompts
1
#2 opened 3 days ago
by
BigDong
updated
a
dataset
2 days ago
updated
a
Space
5 days ago
updated
a
dataset
5 days ago
liked
a
dataset
6 days ago
posted
an
update
6 days ago
Post
1965
Introducing ๐๐
๐ข๐ง๐๐๐๐ญ๐ก: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
๐ ๏ธ carefully extracting math data from Common Crawl;
๐ iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! ๐
Weโre also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
๐ ๏ธ carefully extracting math data from Common Crawl;
๐ iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! ๐
Weโre also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
updated
a
collection
6 days ago
updated
a
Space
21 days ago
updated
a
dataset
27 days ago
updated
a
Space
28 days ago
liked
a
model
29 days ago
liked
2
datasets
29 days ago
updated
3
models
about 1 month ago
updated
a
dataset
about 1 month ago