87 15 200

t.d.a.g. PRO

sequelbox

sequelbox.bsky.social

AI & ML interests

open source, infinite games. (they/them)

Recent Activity

posted an update 43 minutes ago

NEW EXPERIMENTAL RELEASE: DAG Reasoning is here! - Our first Experimental Reasoning Modality release: create structured, analytical Directed Acyclic Graphs to provide insight into your queries and situations! - Multi-step analysis identifies causal relationships, produces confidence measurements, and forms a single structured graph object. - DAG Reasoning Format provides clear, readable JSON containing structured, useful information; easy to use for creating visualizations, doing analysis, or further conversation with your assistant. - Trained in a variety of subjects for flexible analysis: programming, science, business, economics, finance, law, logistics, management, and more! Our first DAG Reasoning release is Qwen 3, starting off with 8B and 14B! Get 8B: https://huggingface.co/sequelbox/Qwen3-8B-DAG-Reasoning Get 14B: https://huggingface.co/sequelbox/Qwen3-14B-DAG-Reasoning You can also get the DAG Reasoning dataset, to train your own models to use DAG Reasoning Format: https://huggingface.co/datasets/sequelbox/DAG-Reasoning-DeepSeek-R1-0528 Support our experimental open-source research efforts, models and datasets: https://huggingface.co/spaces/sequelbox/SupportOpenSource with love, allegra

liked a model about 1 hour ago

sequelbox/Qwen3-14B-DAG-Reasoning

published a model about 1 hour ago

sequelbox/Qwen3-14B-DAG-Reasoning

View all activity

Organizations

posted an update 43 minutes ago

Post

NEW EXPERIMENTAL RELEASE: DAG Reasoning is here!

- Our first Experimental Reasoning Modality release: create structured, analytical Directed Acyclic Graphs to provide insight into your queries and situations!
- Multi-step analysis identifies causal relationships, produces confidence measurements, and forms a single structured graph object.
- DAG Reasoning Format provides clear, readable JSON containing structured, useful information; easy to use for creating visualizations, doing analysis, or further conversation with your assistant.
- Trained in a variety of subjects for flexible analysis: programming, science, business, economics, finance, law, logistics, management, and more!

Our first DAG Reasoning release is Qwen 3, starting off with 8B and 14B!
Get 8B: sequelbox/Qwen3-8B-DAG-Reasoning
Get 14B: sequelbox/Qwen3-14B-DAG-Reasoning

You can also get the DAG Reasoning dataset, to train your own models to use DAG Reasoning Format: sequelbox/DAG-Reasoning-DeepSeek-R1-0528

Support our experimental open-source research efforts, models and datasets: sequelbox/SupportOpenSource

with love,
allegra

posted an update 14 days ago

Post

2551

Some new releases:

- brought the new Shining Valiant 3 series (science-reasoning, AI-reasoning, general chat) to Qwen 3 4B: ValiantLabs/Qwen3-4B-ShiningValiant3
- merged models for Shining Valiant 3 and Esper 3, combining their technical expertise and reasoning skills:
4b: sequelbox/Qwen3-4B-PlumEsper
8b: sequelbox/Qwen3-8B-PlumEsper

coming up we'll have some experimental reasoning releases - datasets and models will be out soon!

also will be bringing SV3 and Esper 3 to more models.

lets keep working for open source :)

love,
allegra

posted an update 20 days ago

Post

2207

NEW RELEASE: Shining Valiant 3!

- Cutting edge science-reasoning: sequelbox/Celestia3-DeepSeek-R1-0528 for physics, biology, chemistry, compsci, astronomy, Earth science, and information theory
- AI to build AI: the all-new sequelbox/Mitakihara-DeepSeek-R1-0528 dataset for high-quality reasoning performance on AI, MLOps, math and CUDA, complex adaptive and agentic systems, cognition, logic, linguistics, simulation, knowledge management, and more!
- Creative reasoning and general chat performance supplemented with sequelbox/Raiden-DeepSeek-R1

Our first release in the SV3 series is Qwen 3, starting off with 8B and 1.7B.
Get 8B: ValiantLabs/Qwen3-8B-ShiningValiant3
Get 1.7B: ValiantLabs/Qwen3-1.7B-ShiningValiant3

We want to bring SV3 to larger models ASAP. Help us out: sequelbox/SupportOpenSource

This is the most excited we've ever been for a release. We hope you enjoy Shining Valiant 3 as much as we do!

With friendship, for the future,
allegra

posted an update 28 days ago

Post

1839

The full Celestia 3 science-reasoning dataset is here!

- 91k high-quality synthetic science prompts answered by DeepSeek-R1-0528
- subjects include physics, biology, chemistry, computer science, Earth science, astronomy, and information theory
- one of the reasoning datasets powering the upcoming Shining Valiant 3 :) coming soon!

GET IT NOW, FOR EVERYONE: sequelbox/Celestia3-DeepSeek-R1-0528
SUPPORT OUR RELEASES: sequelbox/SupportOpenSource

with love,
allegra

2 replies

posted an update about 1 month ago

Post

1068

a list of what's coming up soon from us:

- Shining Valiant 3 for Valiant Labs, powered by the full size Celestia 3 and other soon to be released high-difficulty reasoning datasets
- a new type of reasoning model and dataset we're very excited about - would love to bring out an alpha release here as soon as possible
- more model releases for Esper 3 (weigh in if there are any models you'd like us to prioritize!)
- other New Things

not sure of the exact release order yet, but we'll look to get everything out as quick as we can :)

with excitement,
allegra

posted an update about 2 months ago

Post

1103

EARLY SNEAK PREVIEW: get a first look at the Celestia 3 science-reasoning dataset, built with DeepSeek's newest R1-0528 reasoning model! Subjects include physics, chemistry, biology, computer science, Earth science, astronomy, and information theory.

This early look contains the first 14k rows, all synthetic responses using deepseek-ai/DeepSeek-R1-0528

SEE IT HERE: sequelbox/Celestia3-DeepSeek-R1-0528-PREVIEW

Support our releases: sequelbox/SupportOpenSource

Coming up we'll have more dataset releases, including some novel reasoning and analysis methods - we think an important role for open source researchers is experimenting with new response styles on top of the increasingly excellent base models available to finetune.

more to come soon!
allegra

posted an update about 2 months ago

Post

327

NEW RELEASE: we've brought Esper 3 to the new deepseek-ai/DeepSeek-R1-0528-Qwen3-8B model!

- A full-stack software assistant: a reasoning finetune focused on coding, architecture, and DevOps using the Titanium and Tachibana datasets!
- Improved general and creative reasoning skills, powered by the Raiden dataset.

Get the newest Esper 3: ValiantLabs/DeepSeek-R1-0528-Qwen3-8B-Esper3
Support our releases: sequelbox/SupportOpenSource

more on the way next week!

celestially yours ;)
allegra

replied to their post 2 months ago

we'll be expanding Qwen sizes in both directions :) thanks for your review!

posted an update 2 months ago

Post

330

Updates for the week:
- released some new merge models using ValiantLabs/Qwen3-14B-Esper3 and other Qwen 3 14b finetunes - these merges include math, Web3, uncensored, and general mix. depending on your use case for Esper 3 these may be helpful to you! find them at @sequelbox
- coming up we'll have more model sizes for Esper 3 and Cobalt 2, releasing soon!
- also super excited for more dataset releases with the newly released deepseek-ai/DeepSeek-R1-0528

Support the above efforts and others: sequelbox/SupportOpenSource

back to building :)

2 replies

reacted to lukmanaj's post with 👍 2 months ago

Post

2413

I am so happy to share to all that I’ve just completed the first unit of the new MCP course on Hugging Face and earned my certificate! The AI acceleration track is intense and fast-paced, but I’m doing my best to keep up. Excited for what’s ahead!

1 reply

posted an update 2 months ago

Post

1874

NEW RELEASE: Cobalt 2 for Qwen 3 14b!

- A math-reasoning finetune, focused on high-difficulty math questions with the zwhe99/DeepMath-103K dataset!
- Improved general and creative reasoning skills, powered by the Raiden dataset

GET IT NOW: ValiantLabs/Qwen3-14B-Cobalt2
HELP US RELEASE FASTER: sequelbox/SupportOpenSource

we've got more releases to come soon - excited to share with everyone!

love,
allegra

posted an update 2 months ago

Post

1285

Esper 3 is now available for Qwen 3 14b!

- A full-stack software assistant: a reasoning finetune focused on coding, architecture, and DevOps using the Titanium and Tachibana datasets!
- Improved general and creative reasoning skills, powered by the Raiden dataset.

GET IT NOW: ValiantLabs/Qwen3-14B-Esper3
HELP US RELEASE FASTER: sequelbox/SupportOpenSource

more to come :)
allegra

posted an update 3 months ago

Post

2696

NEW RELEASE: Esper 3 for Qwen 3!

- A full-stack software assistant: a reasoning finetune focused on coding, architecture, and DevOps using the Titanium and Tachibana datasets!
- Improved general and creative reasoning skills, powered by the Raiden dataset.

4B model: ValiantLabs/Qwen3-4B-Esper3
8B model: ValiantLabs/Qwen3-8B-Esper3

We'll also be bringing Esper 3 to larger Qwen 3 models as soon as we can - if you want these, consider helping us out: sequelbox/SupportOpenSource

More models and datasets to come soon!

with my love and enthusiasm,
allegra

posted an update 4 months ago

Post

1788

TITANIUM 2 Deepseek-R1 dataset is here! Open-source synthetic architecture and DevOps dataset: sequelbox/Titanium2-DeepSeek-R1

Esper 3 will be coming out soon for multiple base models, trained on Titanium, Raiden, and more :)

with my love,
allegra

reacted to mkurman's post with ❤️ 5 months ago

Post

3711

Introducing a new architecture, MedIT One – a single-token transformer with LSTM-like recurrence.

It is extremely fast in training and inference, but we lack funding for large-scale training. Enjoy 🍓

https://github.com/MedITSolutionsKurman/medit-one

reacted to singhsidhukuldeep's post with 👍 5 months ago

Post

6996

Exciting New Tool for Knowledge Graph Extraction from Plain Text!

I just came across a groundbreaking new tool called KGGen that's solving a major challenge in the AI world - the scarcity of high-quality knowledge graph data.

KGGen is an open-source Python package that leverages language models to extract knowledge graphs (KGs) from plain text. What makes it special is its innovative approach to clustering related entities, which significantly reduces sparsity in the extracted KGs.

The technical approach is fascinating:

1. KGGen uses a multi-stage process involving an LLM (GPT-4o in their implementation) to extract entities and relations from source text
2. It aggregates graphs across sources to reduce redundancy
3. Most importantly, it applies iterative LM-based clustering to refine the raw graph

The clustering stage is particularly innovative - it identifies which nodes and edges refer to the same underlying entities or concepts. This normalizes variations in tense, plurality, stemming, and capitalization (e.g., "labors" clustered with "labor").

The researchers from Stanford and University of Toronto also introduced MINE (Measure of Information in Nodes and Edges), the first benchmark for evaluating KG extractors. When tested against existing methods like OpenIE and GraphRAG, KGGen outperformed them by up to 18%.

For anyone working with knowledge graphs, RAG systems, or KG embeddings, this tool addresses the fundamental challenge of data scarcity that's been holding back progress in graph-based foundation models.

The package is available via pip install kg-gen, making it accessible to everyone. This could be a game-changer for knowledge graph applications!

posted an update 6 months ago

Post

2845

Raiden is here! 63k creative-reasoning and analytic-reasoning prompts answered by DeepSeek's 685b R1 model!

- All prompts from microsoft/orca-agentinstruct-1M-v1 and all responses from deepseek-ai/DeepSeek-R1
- A deep look at R1's reasoning skills! Use as you will.

Get it now: sequelbox/Raiden-DeepSeek-R1

for everyone :)

reacted to rubenroy's post with 🚀 6 months ago

Post

2664

🔥🚀 Hey everyone! I'm excited to share my latest LLM release: Gilgamesh 72B, a model built on Qwen 2.5-72B Instruct. Gilgamesh was trained on a couple of my GammaCorpus datasets, specifically:

- rubenroy/GammaCorpus-CoT-Math-170k
- rubenroy/GammaCorpus-v2-5m
- rubenroy/GammaCorpus-Fact-QA-450k

I've submitted GGM 72B to the Open LLM Leaderboard for benchmarking, I'll send an update post once the results are in!

You can try it out and share your feedback, check out the model page and see what it can do:
👉 rubenroy/Gilgamesh-72B

Would love to hear your thoughts!

posted an update 6 months ago

Post

1951

New sneak preview of my next release! Raiden is a deepseek-ai/DeepSeek-R1 synthetic dataset that uses creative-reasoning and analytic-reasoning prompts!

This preview release has the first 5.8k rows, all responses generated using DeepSeek's 685b parameter R1 model: https://huggingface.co/datasets/sequelbox/Raiden-DSR1-PREVIEW

Enjoy this look at R1's reasoning skills! Full dataset coming soon.

reacted to victor's post with 🚀 6 months ago

Post

3358

Finally, an open-source AI that turns your lyrics into full songs is here—meet YuE! Unlike other tools that only create short clips, YuE can make entire songs (up to 5 minutes) with vocals, melody, and instruments all working together. Letsss go!

m-a-p/YuE-s1-7B-anneal-en-cot

t.d.a.g. PRO

AI & ML interests

Recent Activity

Organizations

sequelbox's activity