Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning
Paper
•
2505.16088
•
Published
•
3
Speech Recognition Community Event Version 2
non-profit
AI & ML interests
Multi-Lingual Speech Recognition
Recent Activity
View all activity
speech-recognition-community-v2's activity
gagan3012
authored
a
paper
11 days ago
w11wo
authored
a
paper
18 days ago
nouamanetazi
authored
a
paper
about 2 months ago
anton-l
authored
a
paper
about 2 months ago
emre
authored
a
paper
2 months ago
Post
3468
having trouble with auto train
hello there this is the first time i am testing auto train with a 1.8k SFT dataset. Howevery i am not quite sure the training is going smooth. Logs seem quite confusing, token did not match can not auth, generates confusing train splits, do you know how i can check my running job properly?
what is being used for training as data?
any ideas?
hello there this is the first time i am testing auto train with a 1.8k SFT dataset. Howevery i am not quite sure the training is going smooth. Logs seem quite confusing, token did not match can not auth, generates confusing train splits, do you know how i can check my running job properly?
what is being used for training as data?
any ideas?
- 1 reply
w11wo
authored
a
paper
3 months ago
anton-l
authored
a
paper
4 months ago
morenolq
authored
a
paper
4 months ago
gagan3012
authored
a
paper
6 months ago
Post
2921
Introducing 📐𝐅𝐢𝐧𝐞𝐌𝐚𝐭𝐡: 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:
🛠️ carefully extracting math data from Common Crawl;
🔎 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! 🚀
We’re 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:
🛠️ carefully extracting math data from Common Crawl;
🔎 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! 🚀
We’re also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
Rolv-Arild
authored
a
paper
6 months ago
versae
authored
a
paper
6 months ago
gagan3012
authored
a
paper
7 months ago
w11wo
authored
a
paper
7 months ago
pere
authored
4
papers
8 months ago
Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model
Paper
•
2104.09617
•
Published
Boosting Norwegian Automatic Speech Recognition
Paper
•
2307.01672
•
Published
•
1
Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges
Paper
•
2402.01917
•
Published
COVID-Twitter-BERT: A Natural Language Processing Model to Analyse COVID-19 Content on Twitter
Paper
•
2005.07503
•
Published
patrickvonplaten
authored
a
paper
8 months ago