89 15 207

t.d.a.g. PRO

sequelbox

sequelbox.bsky.social

AI & ML interests

open source, infinite games. (they/them)

Recent Activity

liked a model about 6 hours ago

openai/gpt-oss-20b

liked a model 1 day ago

mradermacher/Qwen3-14B-Esper3-i1-GGUF

liked a model 1 day ago

ertghiu256/Qwen-3-1.7b-deepseek-r1-0528-distillation

View all activity

Organizations

liked a model about 6 hours ago

openai/gpt-oss-20b

Text Generation • 12B • Updated about 2 hours ago • 6.82k • • 1.1k

liked 2 models 1 day ago

#2 opened 3 days ago by

reactkick

liked a model 1 day ago

Qwen/Qwen-Image

Text-to-Image • Updated about 21 hours ago • 19k • • 952

liked a model 6 days ago

mradermacher/Qwen3-14B-DAG-Reasoning-GGUF

15B • Updated 6 days ago • 300 • 1

New activity in sequelbox/Mitakihara-DeepSeek-R1-0528 6 days ago

[bot] Conversion to Parquet

#1 opened 29 days ago by

parquet-converter

liked 2 models 6 days ago

DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x

Text Generation • 21B • Updated 6 days ago • 15 • 2

Qwen/Qwen3-30B-A3B-Thinking-2507

Text Generation • 31B • Updated 6 days ago • 32.9k • 176

posted an update 8 days ago

Post

2244

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