Search public pages, research tools, and SAVRN solutions.
Open-weight model · Text classification
by Kim JooYoon/riidolaya-development-claim-hints-v0.1
riidolaya-development-claim-hints-v0.1 is an open-weight model for text classification from Kim, released under Apache License 2.0. Its published files total 1.5 MB.
This original CPU-only Go classifier separately estimates response requests, current development work and completion reports. Each head has true/false/unknown classes. It generates no prose and never verifies task completion or authorizes application writes.
By Kim, published under apache-2.0, revision 4a8c0efaa06f.
This original CPU-only Go classifier separately estimates response requests, current development work and completion reports. Each head has true/false/unknown classes. It generates no prose and never verifies task completion or authorizes application writes. This version is not operationally qualified. On 240 original AI-reviewed development rows, gated true proposals/correct were KO: response1/1, activity7/7, completion0/0 (undefined precision); EN: response6/6, activity6/6, completion3/4. Pooled completion precision was75%, below the frozen98% research floor. Unknown activity/completion references had only3 families per locale, below the minimum5. Few perfect proposals do not establish…
This original CPU-only Go classifier separately estimates response requests, current development work and completion reports. Each head has true/false/unknown classes. It generates no prose and never verifies task completion or authorizes application writes.
This version is not operationally qualified. On 240 original AI-reviewed development rows, gated true proposals/correct were KO: response1/1, activity7/7, completion0/0 (undefined precision); EN: response6/6, activity6/6, completion3/4. Pooled completion precision was75%, below the frozen98% research floor. Unknown activity/completion references had only3 families per locale, below the minimum5. Few perfect proposals do not establish production precision. Calibration/final test were not executed. The private exposed diagnostic also abstained, which is not semantic success.
The model contains18,441 float32 parameters in a 73,988-byte RSC artifact. This is not1.58-bit quantization, a Laya checkpoint, LoRA or fine-tuning of parent weights. Features are unchanged signed word/character hashes from the Apache-2.0 Go repository. Fresh zero initialization, three-head categorical cross entropy, AdamW0.001/decay0.01,40epochs/batch32/seed1729/T1 produced2,120 actual updates. A single local Fit/evaluation/save/reload command took0.83s with peak RSS13,975,552bytes. Artifact size is not process memory; this is one observation, not an inference SLA. See aggregate results and limitations in the JSON files.
Training contains840 original bilingual fictional families /1,680rows /280related story groups. Each language was manually judged; separate AI reviewers saw text without author labels before any outputs. Eleven training-row disagreements were adjudicated with originals preserved. AI annotations and correlated author context are not human gold. Three situations in a story are not independent samples. Only original training prose is packaged; no validation/calibration/test prose, private work, raw predictions or profiles are uploaded.
Use Go1.27.1 and the source revision linked below. Download this repository at a verified immutable commit, verify the package/model SHA, and load explicitly:
go build -trimpath -o riidolaya ./cmd/riidolaya
./riidolaya claims --model claims.rsc --text 'The type check passed and I am running regression tests now.' --json
printf '%s\n' '{"text":"An original fictional development comment."}' |
./riidolaya claims --model claims.rsc --jsonl
The warm JSONL command loads once and reuses a caller-owned workspace. Output mode is research_preview, with semantic_quality_qualified:false and mutation_executed:false. winner is the raw class; state reflects fixed0.9 confidence/0.05 margin abstention. semantic_unknown differs from low_confidence. False means no corresponding positive work report; it never means the task is unfinished. Attribution and scope must be checked by a real adapter.
RSC is distinct from RSH/RSM/RSP: use pkg/statehintclaims.Load, not a parent loader. example.go demonstrates the SDK. Old models and gates are unchanged. Sources: PR175, pinned source. Shout-out to laya.tools. 한국어 안내.
16 files, 1.5 MB in total.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| PACKAGE-MANIFEST.json | Configuration | 2.3 KB | — |
| PROVENANCE.json | Configuration | 1.3 KB | — |
| RECIPE.json | Configuration | 173 B | — |
| RESULTS.development.json | Configuration | 6.1 KB | — |
| SOURCE-MANIFEST.json | Configuration | 970 B | — |
| VALIDATION-SCREENING.json | Configuration | 1.4 KB | — |
| LICENSE | Documentation | 10.2 KB | — |
| NOTICE | Documentation | 280 B | — |
| README.ko.md | Documentation | 3.2 KB | — |
| README.md | Documentation | 3.5 KB | — |
| RUBRIC.en.md | Documentation | 4.8 KB | — |
| RUBRIC.ko.md | Documentation | 5.7 KB | — |
| claims.rsc | Other | 74.0 KB | — |
| example.go | Other | 770 B | — |
| training.original.ai-reviewed.jsonl | Other | 1.4 MB | — |
| .gitattributes | Repository | 1.5 KB | — |
Released by Kim through its official repository on Hugging Face. Read the license.
Yes. riidolaya-development-claim-hints-v0.1 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval. This model is suitable for English. 0 -> Negative; 1 -> Neutral; 2 -> Positive This sentiment analysis model has been integrated into TweetNLP. You can access the demo here.
FinBERT is a BERT model pre-trained on financial communication text. The purpose is to enhance financial NLP research and practice. It is trained on the following three financial communication corpus. The total corpora size is 4.9B tokens. More technical details on FinBERT: Click Link This released finbert-tone model is the FinBERT model fine-tuned on 10,000 manually annotated (positive, negative, neutral) sentences from analyst reports. This model achieves superior performance on financial tone analysis task. If you are simply interested in using FinBERT for financial tone analysis, give it a try. If you use the model in your academic work, please cite the following paper: Huang, Allen H.…
https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details). This model has been integrated into the TweetNLP library.
The huggingface models currently give different results to the detoxify library (see issue here). For the most up to date models we recommend using the models from https://github.com/unitaryai/detoxify Trained models & code to predict toxic comments on 3 Jigsaw challenges: Toxic comment classification, Unintended Bias in Toxic comments, Multilingual toxic comment classification. Built by Laura Hanu at Unitary, where we are working to stop harmful content online by interpreting visual content in context. Score not directly comparable since it is obtained on the validation set provided and not on the test set. To update when the test labels are made available. It is also noteworthy to mention…
With this model, you can classify emotions in English text data. The model was trained on 6 diverse datasets (see Appendix below) and predicts Ekman's 6 basic emotions, plus a neutral class: 1) anger 2) disgust 3) fear 4) joy 5) neutral 6) sadness 7) surprise The model is a fine-tuned checkpoint of DistilRoBERTa-base. For a 'non-distilled' emotion model, please refer to the model card of the RoBERTa-large version. a) Run emotion model with 3 lines of code on single text example using Hugging Face's pipeline command on Google Colab: b) Run emotion model on multiple examples and full datasets (e.g.,.csv files) on Google Colab: Please reach out to [email protected] if you have any…