Hugging Face's logo
Activity Feed

AI & ML interests

Intelligence for everyone.

Recent Activity
doofz  new activity about 5 hours ago
HAL-X-AI/THX-02:Demo for this model on Spaces
doofz  published a model about 11 hours ago
HAL-X-AI/THX-02
doofz  updated a model 1 day ago
HAL-X-AI/THX-02
View all activity
doofz 
in HAL-X-AI/THX-02 about 5 hours ago

Demo for this model on Spaces

1
#1 opened about 5 hours ago by
multimodalart
doofz 
posted an update about 10 hours ago
view post
Post
38
THX-02 is here. Our new open-source Thinking Decision Model.

Today we open-sourced THX-02, our second-generation 4.5B-parameter decision model, developed at HAL-X AI and launched in collaboration with ModelScope (Alibaba) with FREE API, check below for documentation.

Unlike traditional decision models, THX-02 introduces adaptive reasoning. It thinks when a decision is complex or uncertain, and answers directly when reasoning isn't needed, typically in under 100 ms.

Decision Index 0.3 (37 decision tasks):
- 65.06 with reasoning
- 63.83 without reasoning
- Outperforms TypeSafe Jev and decision models up to 6× its size

THX-02 supports calibrated probabilities, multilingual decision-making, and native reasoning, with special attention to Azerbaijani and other underrepresented languages.

Fully open-source under Apache 2.0:
- 4.5B parameters
- Adaptive thinking and non-thinking modes
- Weights, reasoning adapter, runtime, and server available
- Self-hostable on your own infrastructure
- Python: pip install thx02

Model (Hugging Face):
HAL-X-AI/THX-02

ModelScope:
https://modelscope.ai/models/HAL-X/THX-02

Free API & Documentation:
https://api.hal-x.ai/docs/thx-02
doofz 
published a model about 11 hours ago
doofz 
updated a model 1 day ago
doofz 
posted an update 27 days ago
view post
Post
3,780
THX-01 now has a free API. No key, no sign-up.
Yesterday we open-sourced THX-01, our 322M decision model. Today we're opening the hosted API to everyone for free.

Send a message or document with typed questions and get every answer in one forward pass, about 10 ms, with a calibrated probability for each option:

curl https://api.hal-x.ai/v1/systemone \
-H "Content-Type: application/json" \
-d '{"state": "My card was charged twice for one order", "questions": {"team": {"type": "choice", "question": "Which team handles this?", "criteria": {"billing": "billing", "tech": "technical", "sales": "sales"}}}}'

What it answers: choice, yes/no, score, exact number from the text (or null if it isn't there), verbatim excerpt, and "cite": true for supporting passages.

- Free tier: 200 decisions per minute per IP
- On our 2,843-ticket benchmark in four languages: 98.4% vs 97.4% for TypeSafe Jev, at about 10 ms instead of 331 ms
- 18 trained languages
- Weights are Apache 2.0: pip install thx01

Model: doofz/THX-01
Demo: doofz/THX-01-demo
doofz 
posted an update 28 days ago
view post
Post
2,164
We just open-sourced THX-01, a 322M decision model.

Most AI decisions in production are classification in disguise: which team gets this ticket, is this email phishing, what's the total on this invoice. Calling a large LLM for each one is slow, expensive, and its confidence means nothing.

THX-01 is built for exactly these decisions. You send it a message or document plus typed questions, and in one forward pass (~10 ms) it returns:
- an answer to every question, with a calibrated probability for each option
- exact numbers stated in the document, or null if the number isn't there
- verbatim quotes and the passages that support each answer

On our 4-language support-ticket benchmark it matches Claude Sonnet 5.5 (98.4 vs 98.5) and is about 150x faster.
Because its confidence is calibrated, it handled about 75% of tickets automatically with zero errors.

pip install thx01
doofz/THX-01
  • 4 replies
·