doofz/THX-01
text-classification model by doofz
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
THX-01 is a non-autoregressive, multilingual decision model developed by HAL-X AI. Given a state (a message, ticket, e-mail, document, JSON record or agent trace) and one or more typed questions written in natural language, it returns a calibrated answer to every question in a single forward pass of about 10 ms on one GPU. THX-01 is trained with large-scale Reinforcement Learning for Calibrated Decisions (RLCD): the reward is a strictly proper scoring rule, so reporting honest probabilities is the only way to maximise it. Beyond choosing among options, THX-01 can return numbers stated in a document, verbatim excerpts and supporting citations, through the same interface. number, excerpt and citations are native THX-01 capabilities. They are not part of the TypeSafe question types (choice, noul, score), where they have to be emulated in the service layer with repeated choice calls. THX-01 also answers such emulation calls (value-range buckets and document chunks)…
Read the full model card ↗ · Preview checked 2026-10-30T04:48:33.750Z
Inside the original model card — Document outline
- THX-01
- Contents
- Question types
- Quickstart
- Benchmarks
- Support-ticket classification
- Extraction and citation
- Calibration and selective automation
- Multilingual decision suite
- Speed
- Method
- Reinforcement Learning for Calibrated Decisions
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
doofz/THX-01 is a text-classification model repository published by doofz on Hugging Face. The source reports the thx01 library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-classification
- Library
- thx01
- Recent downloads (30 days)
- 631
- Cumulative likes
- 81
- Hugging Face trending score
- 70
- Reported safetensors parameters
- 321,908,998
- Architecture
- THXDecisionModel
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-23T12:59:53.000Z
- Last modified
- 2026-10-16T16:22:07.000Z
Compatibility and lineage
Reported languages: az, en, ru, tr, de, fr, es, ar, hi, zh, fa, ka, ja, ko, uk, kk, uz, it, multilingual
Reported base models: jhu-clsp/mmBERT-base
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-18T06:42:00.150Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.