Hugging Face's logo

Data is Better Together - Russian Language Team

community
Activity Feed Request to join this org

AI & ML interests

Russian speakers working on prompt translation as a part of the Data is Better Together initiative, building impactful community datasets.

DIBT-Russian's activity

ZennyKennyΒ 
posted an update about 14 hours ago
view post
Post
440
Community! πŸ’‘πŸ’‘πŸ’‘

It's the last day to submit your datasets for the Reasoning Datasets Competition: https://www.bespokelabs.ai/blog/reasoning-datasets-competition

Here are my submissions:
- ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset
- ZennyKenny/cosa-benchmark-dataset
- ZennyKenny/tactical-military-reasoning-v.1.0
- ZennyKenny/tron-dataset-v.1.0

Have a look and drop a ❀️ or comment! Check out the entire collection of submissions here: https://huggingface.co/datasets?other=reasoning-datasets-competition
ZennyKennyΒ 
posted an update 3 days ago
view post
Post
3017
After hearing the news that Marc Andreessen thinks that the only job that is safe from AI replacement is venture capital: https://gizmodo.com/marc-andreessen-says-one-job-is-mostly-safe-from-ai-venture-capitalist-2000596506 🧠🧠🧠

The Reasoned Capital synthetic dataset suddenly feels much more topical: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset πŸ”₯πŸ”₯πŸ”₯

Really looking forward to potentially expanding this architecture and seeing how algorithmic clever investment truly is! πŸ’°πŸ’°πŸ’°
ZennyKennyΒ 
posted an update 4 days ago
view post
Post
3290
When I heard the Reasoning Dataset Competition deadline was extended to 9 May, I knew I had time to get in one more entry. πŸ”₯πŸ”₯πŸ”₯

With the rise of Vibe Coding, and the potential risks that are introduced by humans letting LLMs build their apps for them, lots of people are (rightfully) concerned about the safety of the code that is hitting prod.

In response to that, I'm happy to present my final submission to the Reasoning Dataset Competition and attempt to start benchmarking the ability of LLMs to identify unsafe and / or exploitable code by way of the CoSa (Code Safety) benchmark: ZennyKenny/cosa-benchmark-dataset

Currently a curated set of 200 examples, calibrated on OpenAI's standard issue models (GPT-4.1, o4 mini, and GPT-3.5 Turbo) as "baseline performance" (70% decile). Check it out and drop a ❀️ if you think it could be useful or hit the Community section with suggestions / critiques.
  • 2 replies
Β·
ZennyKennyΒ 
posted an update 9 days ago
view post
Post
1349
The same way the advent of Adobe Illustrator has led to innovation in the way that creative professionals work, I earnestly believe that AI will do the same (contrary to the popular opinion that it represents some regression in the world of creatives).

@natalika and I were speaking about this topic and like most illustrators she has some understandable concerns about the spread of AI in her field. She also told me how much time she spends generating concept art that will never see the light of day in >98% of cases. πŸ’‘

To me, that sounded like a perfect opportunity to leverage image diffusion in a way that helps artists spend more time creating cool stuff rather than just malevolently mining their work and using it without credit. Using the Black Forest Labs base model FLUX, Replicate, and about $5 of H100 compute, I post-trained a LoRA adapter on a set of her images associated with one project she's working on and spun up an app with Hugging Face Spaces (and Zero GPU for the win).

I give you, Natalie Diffusion: ZennyKenny/natalie-diffusion

Now, generating concept art in her particular style takes seconds instead of hours and when it's time to put the work into production, a human designer is still invaluable. And building it in the open hopefully inspires other use cases amongst other designers. πŸ––
  • 2 replies
Β·
ZennyKennyΒ 
posted an update 10 days ago
view post
Post
2709
I've created a new dataset using the Algorithm of Thoughts architecture proposed by Sel et al. (2023) in a reasoning context. (paper: https://arxiv.org/pdf/2308.10379)

The dataset simulates the discovery phase of a fictitious VC firm called Reasoned Capital and, once expanded, can be used to create models which are able to make complex, subjective financial decisions based on different criteria.

The generation process encourages recursive problem-solving in increasingly complex prompts to encourage models to assess and reevaluate the conclusions and generated opinions of upstream models. Pretty neat stuff, and I'm not aware of this architecture being used in a reasoning context anywhere else.

Check it out: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset
ZennyKennyΒ 
posted an update 13 days ago
view post
Post
553
Phew, maybe a little dark, but I've submitted my second dataset to the Reasoning Datasets Competition: ZennyKenny/tactical-military-reasoning-v.1.0

I'd be interested to hear the community's thoughts on the applications of AI in the military. Especially in the wargaming space.

This is something that feels inevitable (and realistically, probably already in progress). Doesn't it make sense for us to have an understanding of the mechanics of such processes? Surely they will never be open source.
Β·
ZennyKennyΒ 
posted an update 22 days ago
view post
Post
1431
Submitted my first dataset for the Reasoning Datasets Competition! https://huggingface.co/datasets/ZennyKenny/TRON-dataset-v.1.0

This dataset is designed to post-train Metareasoning agents, or those agents whose job it is to quickly (and importantly, cheaply) reason through whether it makes sense to launch a full reasoning job or simply use a simple completions job.

There's still plenty of time to join the competition! https://www.bespokelabs.ai/blog/reasoning-datasets-competition

Generation notebook (linked in dataset) is open source and pretty well generalized if I don't say so myself, so you can use it to make your own Metareasoning datasets.

Shoutout to @onekq for his inspiring comment on this topic.
ZennyKennyΒ 
posted an update 29 days ago
ZennyKennyΒ 
posted an update about 1 month ago
view post
Post
2131
A few new Russian-language synthetic datasets. The labelling is good, but some of the syntax and grammar is not great.

Great for Russian-language classification models, probably not great for fine-tuning Russian-langauge text generation.

- Virtual Assistant Query / Responses: ZennyKenny/ru_virtual_assistant_chatgpt_distill
- LLM Query / Responses: ZennyKenny/russian_llm_response_chatgpt_distill

Crazy how much language drift is still an issue, especially given that Russian constitutes nearly 5% of the content on the internet.
ZennyKennyΒ 
posted an update about 1 month ago
view post
Post
1939
Besides being the coolest named benchmark in the game, HellaSwag is an important measurement of Π·Π΄Ρ€Π°Π²Ρ‹ΠΉ ΡΠΌΡ‹ΡΠ»ΡŒ (or common sense) in LLMs.

- More on HellaSwag: https://github.com/rowanz/hellaswag

I spent the afternoon benchmarking YandexGPT Pro 4th Gen, one of the Russian tech giant's premier models.

- Yandex HF Org: yandex
- More on Yandex models: https://yandex.cloud/ru/docs/foundation-models/concepts/yandexgpt/models

The eval notebook is available on GitHub and the resulting dataset is already on the HF Hub!

- Eval Notebook: https://github.com/kghamilton89/ai-explorer/blob/main/yandex-hellaswag/hellaswag-assess.ipynb
- Eval Dataset: ZennyKenny/yandexgptpro_4th_gen-hellaswag

And of course, everyone wants to see the results so have a look at the results in the context of other zero-shot experiments that I was able to find!
  • 2 replies
Β·
ZennyKennyΒ 
posted an update 2 months ago
view post
Post
530
It took me a while, but I've finally got it working: ZennyKenny/note-to-text

Using a Meta LLaMa checkpoint from Unsloth and some help from the HF community, you can capture handwritten notes and convert them into digital format in just a few second.

Really exciting times for AI builders on Hugging Face.
  • 2 replies
Β·
ZennyKennyΒ 
posted an update 2 months ago
view post
Post
1914
I've spent most of time working with AI on user-facing apps like Chatbots and TextGen, but today I decided to work on something that I think has a lot of applications for Data Science teams: ZennyKenny/comment_classification

This Space supports uploading a user CSV and categorizing the fields based on user-defined categories. The applications of AI in production are truly endless. πŸš€
ZennyKennyΒ 
posted an update 3 months ago
view post
Post
2233
Really excited to start contributing to the SWE Arena project: https://swe-arena.com/

Led by IBM PhD fellow @terryyz , our goal is to advance research in code generation and app development by frontier LLMs.
ZennyKennyΒ 
posted an update 3 months ago
view post
Post
1995
Okay this is pretty crazy. Snowflake has CortexAI and Uber is already teasing QueryGPT, both of which prominently feature plain text to SQL features to query your database.

I decided to see how hard it would be to put together something similar using πŸ€— smolagents. Turns out, it was pretty straightforward. I managed to get it done in London Luton airport this afternoon.

ZennyKenny/sqlAgent
  • 2 replies
Β·
ZennyKennyΒ 
posted an update 3 months ago
view post
Post
3470
I've completed the first unit of the just-launched Hugging Face Agents Course. I would highly recommend it, even for experienced builders, because it is a great walkthrough of the smolagents library and toolkit.
ZennyKennyΒ 
posted an update 3 months ago
view post
Post
460
GradientBoostingClassifier is an algorithm supported by the Python SciKit library, and now you can quickly train an ML model using this powerful technique on any (viable) dataset in the Hugging Face Hub without a line of code.

Love finishing a project right when the late night starts to turn into the early morning: sklearn-docs/GradientBoostingClassifier

Long time listener, first time caller, but always pleased to contribute, even if only adjacently, to the power of SciKit.
ZennyKennyΒ 
posted an update 4 months ago
view post
Post
450
Really pleased with the Bring Your Own Model (BYOM) feature in Brave Browser: https://brave.com/blog/byom-nightly/

Takes about 5 minutes to configure your own locally running LLM as an in-browser assistant. Totally local, totally private, totally yours.
  • 1 reply
Β·
ZennyKennyΒ 
posted an update 4 months ago
view post
Post
440
On-demand audio transcription is an often-requested service without many good options on the market.

Using Hugging Face Spaces with Gradio SDK and the OpenAI Whisper model, I've put together a simple interface that supports the transcription and summarisation of audio files up to five minutes in length, completely open source and running on CPU upgrade. The cool thing is that it's built without a dedicated inference endpoint, completely on public infrastructure.

Check it out: ZennyKenny/AudioTranscribe

I wrote a short article about the backend mechanics for those who are interested: https://huggingface.co/blog/ZennyKenny/on-demand-public-transcription
  • 1 reply
Β·
dvilasueroΒ 
authored a paper 5 months ago
dvilasueroΒ 
posted an update 5 months ago
view post
Post
2662
🌐 Announcing Global-MMLU: an improved MMLU Open dataset with evaluation coverage across 42 languages, built with Argilla and the Hugging Face community.

Global-MMLU is the result of months of work with the goal of advancing Multilingual LLM evaluation. It's been an amazing open science effort with collaborators from Cohere For AI, Mila - Quebec Artificial Intelligence Institute, EPFL, Massachusetts Institute of Technology, AI Singapore, National University of Singapore, KAIST, Instituto Superior TΓ©cnico, Carnegie Mellon University, CONICET, and University of Buenos Aires.

🏷️ +200 contributors used Argilla MMLU questions where regional, dialect, or cultural knowledge was required to answer correctly. 85% of the questions required Western-centric knowledge!

Thanks to this annotation process, the open dataset contains two subsets:

1. πŸ—½ Culturally Agnostic: no specific regional, cultural knowledge is required.
2. βš–οΈ Culturally Sensitive: requires dialect, cultural knowledge or geographic knowledge to answer correctly.

Moreover, we provide high quality translations of 25 out of 42 languages, thanks again to the community and professional annotators leveraging Argilla on the Hub.

I hope this will ensure a better understanding of the limitations and challenges for making open AI useful for many languages.

Dataset: https://huggingface.co/datasets/CohereForAI/Global-MMLU