doofz/THX-01
Text Classification • 0.3B • Updated • 41 • 30
Farid Aghayev PRO
doofz
P(doom) 10%
AI & ML interests
Co-Founder & CEO at HAL-X
Recent Activity
liked a model 1 day ago
doofz/THX-01 posted an update 1 day ago
Two days ago, we open-sourced THX-01, our 322M-parameter decision model that outperforms Jev on several benchmarks and can even run locally on a PHONE!
Yesterday, we opened the THX-01 API to everyone for free.
And the response has been incredible. We've already processed:
- 25M+ tokens
- 211,000+ decisions
What's available:
- Free API: 200 decisions/month
- Full model weights, source code, and training scripts
- Apache 2.0 license
- 18 trained languages
- Local inference, even on mobile devices
Everything is open-source, and we're just getting started!
Free API: https://api.hal-x.ai/docs/thx-01
Model & weights: https://huggingface.co/doofz/THX-01
Python: pip install thx01Organizations
liked a
model 1 day ago
posted an update 1 day ago
Post
78
Two days ago, we open-sourced THX-01, our 322M-parameter decision model that outperforms Jev on several benchmarks and can even run locally on a PHONE!
Yesterday, we opened the THX-01 API to everyone for free.
And the response has been incredible. We've already processed:
- 25M+ tokens
- 211,000+ decisions
What's available:
- Free API: 200 decisions/month
- Full model weights, source code, and training scripts
- Apache 2.0 license
- 18 trained languages
- Local inference, even on mobile devices
Everything is open-source, and we're just getting started!
Free API: https://api.hal-x.ai/docs/thx-01
Model & weights: doofz/THX-01
Python: pip install thx01
Yesterday, we opened the THX-01 API to everyone for free.
And the response has been incredible. We've already processed:
- 25M+ tokens
- 211,000+ decisions
What's available:
- Free API: 200 decisions/month
- Full model weights, source code, and training scripts
- Apache 2.0 license
- 18 trained languages
- Local inference, even on mobile devices
Everything is open-source, and we're just getting started!
Free API: https://api.hal-x.ai/docs/thx-01
Model & weights: doofz/THX-01
Python: pip install thx01
upvoted an article 1 day ago
Article
THX-01: We Open-Sourced a 322M Decision Model That Runs on Your Phone and outperforms Jev!
doofz
• • 1 published an article 1 day ago
Article
THX-01: We Open-Sourced a 322M Decision Model That Runs on Your Phone and outperforms Jev!
doofz
• • 1 liked a
Space 2 days ago
reacted to their post with 🔥 2 days ago
Post
2131
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
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
- 1 reply
reacted to their post with 🚀 2 days ago
Post
3535
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
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
posted an update 2 days ago
Post
3535
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
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
updated a
Space 3 days ago
published a
Space 3 days ago
posted an update 3 days ago
Post
2131
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
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
- 1 reply
updated a
model 3 days ago
published a
model 19 days ago