78 8 135

t.d.a.g. PRO

sequelbox

sequelbox.bsky.social

AI & ML interests

open source, infinite games. (they/them)

Recent Activity

updated a dataset 4 days ago

sequelbox/Tachibana-QVQ

updated a dataset 4 days ago

sequelbox/Tachibana-QVQ-PREVIEW

posted an update 4 days ago

NEW RELEASE: the https://huggingface.co/datasets/sequelbox/Tachibana-QVQ dataset is here! Code-reasoning and code-instruct data generated with https://huggingface.co/Qwen/QVQ-72B-Preview Come check out QVQ's coding skills! for everyone to use! more QVQ and Llama 3.1 405b datasets coming soon :)

View all activity

Organizations

sequelbox's activity

posted an update 4 days ago

Post

1313

NEW RELEASE: the sequelbox/Tachibana-QVQ dataset is here! Code-reasoning and code-instruct data generated with Qwen/QVQ-72B-Preview

Come check out QVQ's coding skills!

for everyone to use!

more QVQ and Llama 3.1 405b datasets coming soon :)

reacted to DawnC's post with ❤️ 7 days ago

Post

2168

🌟 PawMatchAI: Making Breed Selection More Intuitive! 🐕
Excited to share the latest update to this AI-powered companion for finding your perfect furry friend! I've made significant architectural improvements to enhance breed recognition accuracy and feature detection.

✨ What's New?
Enhanced breed recognition through advanced morphological feature analysis:
- Implemented a sophisticated feature extraction system that analyzes specific characteristics like body proportions, head features, tail structure, fur texture, and color patterns
- Added an intelligent attention mechanism that dynamically focuses on the most relevant features for each image
- Improved multi-dog detection capabilities through enhanced spatial feature analysis
- Achieved better precision in distinguishing subtle breed characteristics

🎯 Key Features:
Smart breed recognition powered by advanced AI architecture
Visual matching scores with intuitive color indicators
Detailed breed comparisons with interactive tooltips
Lifestyle-based recommendations tailored to your needs

💭 Project Vision
Combining my passion for AI and pets, this project represents another step toward creating meaningful AI applications. Each update aims to make the breed selection process more accessible while improving the underlying technology.

👉 Try it now: DawnC/PawMatchAI

Your likes ❤️ on this space fuel this project's growth!

#AI #MachineLearning #DeepLearning #Pytorch #ComputerVision #TechForLife

2 replies

posted an update 12 days ago

Post

2124

Check out the early preview of the upcoming Tachibana-QVQ dataset: code-reasoning and code-instruct data generated with Qwen/QVQ-72B-Preview

Link here: sequelbox/Tachibana-QVQ-PREVIEW

more to come :)

1 reply

reacted to m-ric's post with 👀 22 days ago

Post

2464

𝐇𝐮𝐠𝐠𝐢𝐧𝐠 𝐅𝐚𝐜𝐞 𝐫𝐞𝐥𝐞𝐚𝐬𝐞𝐬 𝐏𝐢𝐜𝐨𝐭𝐫𝐨𝐧, 𝐚 𝐦𝐢𝐜𝐫𝐨𝐬𝐜𝐨𝐩𝐢𝐜 𝐥𝐢𝐛 𝐭𝐡𝐚𝐭 𝐬𝐨𝐥𝐯𝐞𝐬 𝐋𝐋𝐌 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝟒𝐃 𝐩𝐚𝐫𝐚𝐥𝐥𝐞𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 🥳

🕰️ Llama-3.1-405B took 39 million GPU-hours to train, i.e. about 4.5 thousand years.

👴🏻 If they had needed all this time, we would have GPU stories from the time of Pharaoh 𓂀: "Alas, Lord of Two Lands, the shipment of counting-stones arriving from Cathay was lost to pirates, this shall delay the building of your computing temple by many moons "

🛠️ But instead, they just parallelized the training on 24k H100s, which made it take just a few months.
This required parallelizing across 4 dimensions: data, tensor, context, pipeline.
And it is infamously hard to do, making for bloated code repos that hold together only by magic.

🤏 𝗕𝘂𝘁 𝗻𝗼𝘄 𝘄𝗲 𝗱𝗼𝗻'𝘁 𝗻𝗲𝗲𝗱 𝗵𝘂𝗴𝗲 𝗿𝗲𝗽𝗼𝘀 𝗮𝗻𝘆𝗺𝗼𝗿𝗲! Instead of building mega-training codes, Hugging Face colleagues cooked in the other direction, towards tiny 4D parallelism libs. A team has built Nanotron, already widely used in industry.
And now a team releases Picotron, a radical approach to code 4D Parallelism in just a few hundred lines of code, a real engineering prowess, making it much easier to understand what's actually happening!

⚡ 𝗜𝘁'𝘀 𝘁𝗶𝗻𝘆, 𝘆𝗲𝘁 𝗽𝗼𝘄𝗲𝗿𝗳𝘂𝗹:
Counting in MFU (Model FLOPs Utilization, how much the model actually uses all the compute potential), this lib reaches ~50% on SmolLM-1.7B model with 8 H100 GPUs, which is really close to what huge libs would reach. (Caution: the team is leading further benchmarks to verify this)

Go take a look 👉 https://github.com/huggingface/picotron/tree/main/picotron

1 reply

reacted to takarajordan's post with ❤️ about 1 month ago

Post

2278

I'm super excited to release my first open-source text dataset:

WorldScenario 20K is a novel dataset of 20,000 synthetically generated multi-stakeholder scenarios designed to simulate real-world decision-making processes. Each scenario explores a unique environmental, societal, or economic issue.

I used the brand new meta-llama/Llama-3.3-70B-Instruct model to generate this dataset and I put the dataset through some post processing to clean and evaluate the dataset for diversity.

I'd appreciate some feedback and thoughts on my new release! Thanks!

takarajordan/WorldScenario_20K

8 replies

posted an update about 1 month ago

Post

485

NEW RELEASE: Celestia 2!

- Multi-turn science-instruct conversations in the microsoft/orca-agentinstruct-1M-v1 style, generated by meta-llama/Llama-3.1-405B-Instruct
- 100% challenging, multi-turn conversations focused on physics, chemistry, computer science, biology, Earth science, and more!

Celestia 2 will be one of the datasets used for training by the upcoming agent-instruct model, Shining Valiant 3. very excited for this :)

Get it now: sequelbox/Celestia2

do as you will. there is only the sea.

posted an update about 2 months ago

Post

1245

next version of sequelbox/Celestia will be microsoft/orca-agentinstruct-1M-v1 style. coming soon

1 reply

posted an update 2 months ago

Post

451

NEW RELEASE! Shining Valiant 2 for Llama 3.1 70b is here!

- Trained on high quality science-instruct, complex queries, and general chat data!
- Uses our newest datasets, ALL open-sourced for everyone to use!

GET SV2 70B: ValiantLabs/Llama3.1-70B-ShiningValiant2

- Find the SV datasets here, including the expanded version of our science-instruct dataset:
- sequelbox/Celestia
- sequelbox/Spurline
- sequelbox/Supernova
- SV2 8b and 3b will be updated with the new datasets soon!

Enjoy! :)

posted an update 3 months ago

Post

1239

NEW releases for today:

- We've brought our new Esper 2 model to Llama 3.2! The DevOps-first Esper finetunes use our newest open source datasets. Get the new Esper: ValiantLabs/Llama3.2-3B-Esper2
- Some new merged models, combining Shining Valiant 2 with the other Build Tools:
- sequelbox/Llama3.1-8B-PlumCode
- sequelbox/Llama3.1-8B-PlumChat
- sequelbox/Llama3.1-8B-PlumMath

more to come soon :)

1 reply

replied to their post 3 months ago

ALSO: the newest version of Enigma 8b is out, using the latest versions of Tachibana+Supernova: https://huggingface.co/ValiantLabs/Llama3.1-8B-Enigma

posted an update 3 months ago

Post

396

ESPER 2 IS HERE!

- High quality code-instruct and chat with a DevOps focus: AWS, Azure, GCP, Terraform, Dockerfiles, pipelines, shell scripts and more!
- Powered by our new sequelbox/Titanium dataset, along with the newest versions of sequelbox/Tachibana and sequelbox/Supernova
- Available now for Llama 3.1 8b, more models to come!

Get the model: ValiantLabs/Llama3.1-8B-Esper2

for everyone to use :)
more soon :)

1 reply

posted an update 3 months ago

Post

1499

Llama 3.2 3b + code-instruct: get our newest version of Enigma!

ValiantLabs/Llama3.2-3B-Enigma is trained on our high quality code-instruct ( sequelbox/Tachibana) and general chat ( sequelbox/Supernova) data.

try it now :) more models and datasets coming soon!

posted an update 4 months ago

Post

495

NEW RELEASE! We've brought Shining Valiant 2 to Llama 3.2!

ValiantLabs/Llama3.2-3B-ShiningValiant2 is trained on high-quality general chat and science-instruct data! Get it now :)

(Enigma's up next for 3b, that'll be out soon!)

Additionally, newly expanded versions of the following datasets are now available:

sequelbox/Supernova is now 178k rows of high-quality synthetic general chat data.
sequelbox/Tachibana is now 104k rows of high-quality synthetic code-instruct data.

for everyone to use :)
more soon

reacted to fdaudens's post with 🚀 4 months ago

Post

3354

🚀 1,000,000 public models milestone achieved on Hugging Face! 🤯

This chart by @cfahlgren1 shows the explosive growth of open-source AI. It's not just about numbers - it's a thriving community combining cutting-edge ML with real-world applications. cfahlgren1/hub-stats

Can't wait to see what's next!

2 replies

posted an update 4 months ago

Post

356

today's release: the updated Supernova general chat dataset!

- the new Supernova is 2x the rows, continuing to provide high quality general synthetic data generated with Llama 405b Instruct.

Find it at sequelbox/Supernova

Enjoy! There's also a new version of sequelbox/Llama3.1-8B-MOTH available using the new dataset. (new and better MOTHs for other models will come as well, but the Build Tools and Shining Valiant take priority.)

posted an update 4 months ago

Post

1398

Just released: our newest version of Shining Valiant, powered by an all-new science-instruct dataset!

The model: ValiantLabs/Llama3.1-8B-ShiningValiant2
The dataset: sequelbox/Celestia

tell your friends! for everyone to use.

(more releases coming later this week! including an expansion of the sequelbox/Supernova generalist dataset.)

replied to their post 4 months ago

coming next: newest version of Shining Valiant + the new science-instruct dataset that she'll be using as a knowledge base. very excited for this!
after that more build tool releases :)

posted an update 4 months ago

Post

1221

NEW RELEASE!

- MOTH is a generalist chat model, using high quality synthetic data to improve general performance.
- Currently available for Llama 3.1 and Gemma 2, more models to follow in the future.

get the models:
sequelbox/Llama3.1-8B-MOTH
sequelbox/gemma-2-9B-MOTH

get the dataset:
sequelbox/Supernova

<3 for everyone to use <3

1 reply

reacted to vilarin's post with 🚀 4 months ago

Post

1627

🐣Ai2 Releasing OLMoE!
OLMoE-1B-7B-Instruct is a Mixture-of-Experts LLM with 1B active and 7B total parameters, and, OLMoE is 100% open-source in model, code-base, datasets!

🦖Paper: https://arxiv.org/abs/2409.02060

🤗Model: allenai/OLMoE-1B-7B-0924-Instruct

💾Datasets: allenai/OLMoE-mix-0924

posted an update 4 months ago

Post

711

the new version of Enigma, our code-instruct specialist, is out now:
- ValiantLabs/Llama3.1-8B-Enigma is trained on code-instruct and general chat data.
- the updated code-instruct database is available now as well: sequelbox/Tachibana

more to come soon!