Search public pages, research tools, and SAVRN solutions.
shingi-27b is an open-weight model for text classification from Kortexa.ai, released under Apache License 2.0. Its published files total 7.8 GB. It draws 1.1k downloads a month.
Shingi 27B is a local decision model. You give it context (text, and optionally images), a question and the possible answers. It returns a choice, calibrated probabilities or an ordinal score.
By Kortexa.ai, published under apache-2.0, revision 38eee4b852de.
Shingi 27B is a local decision model. You give it context (text, and optionally images), a question and the possible answers. It returns a choice, calibrated probabilities or an ordinal score. It reads the logit of every candidate answer directly and generates no text. The model is a single 7.2 GB ternary GGUF file (PQ20). It is Bonsai 2 27B with were trained. It needs no adapter. On Linux with an NVIDIA GPU and the CUDA toolkit, or on a Mac with Apple Silicon: This builds the pinned Prism runtime, downloads this model into your Hugging Face cache and serves the API on http://127.0.0.1:8765. Use --port to change the port. The code, API examples and options are in kortexa-ai/shingi-27b.…
Shingi 27B is a local decision model. You give it context (text, and optionally images), a question and the possible answers. It returns a choice, calibrated probabilities or an ordinal score. It reads the logit of every candidate answer directly and generates no text.
The model is a single 7.2 GB ternary GGUF file (PQ2_0). It is Bonsai 2 27B with retrained block scales: the ternary weights are unchanged, only their scales were trained. It needs no adapter.
On Linux with an NVIDIA GPU and the CUDA toolkit, or on a Mac with Apple Silicon:
curl -fsSL https://raw.githubusercontent.com/kortexa-ai/shingi-27b/main/run.sh | bash
This builds the pinned Prism runtime,
downloads this model into your Hugging Face cache and serves the API on
http://127.0.0.1:8765. Use --port to change the port. The code, API examples
and options are in kortexa-ai/shingi-27b.
| Resource | Need |
|---|---|
| GPU | NVIDIA with at least 20 GB: RTX 4090, RTX PRO 6000 or DGX Spark (tested). The model uses about 8 GiB at the 16K context, about 9 GiB with image input. |
| System RAM | about 1 GB for the server process, plus page cache for the 7.2 GB file |
| Disk | 7.2 GB for the weights, plus the runtime build |
| Mac | Apple Silicon with 24 GB or more of unified memory (16 GB minimum), using Metal |
| Software | Linux (x86-64 or aarch64) with the CUDA toolkit, or macOS with the Xcode command line tools; CMake and a C++17 compiler |
Median latency per decision, one request at a time, loading excluded:
| Request | RTX PRO 6000 | RTX 4090 | DGX Spark |
|---|---|---|---|
| Short yes/no (~120 tokens) | 66 ms | 85 ms | 148 ms |
| Short choice, 3 options | 73 ms | 95 ms | 181 ms |
| Choice, 10 options (~1,300 tokens) | 246 ms | 306 ms | 802 ms |
| Long choice, 3 options (~3,000 tokens) | 881 ms | 1,045 ms | 2,984 ms |
| GPU memory in use | 8.3 GB | 8.2 GB | 7.9 GB |
With image input on the RTX 4090, one image and one question take about 0.66 s (median) and the model uses about 9.2 GB.
Questions in one request share a single pass over the images and the state, so extra questions are cheap: on an RTX PRO 6000, eight questions about one image take about 1.8 s instead of 8.7 s.
External suites, canonical choice order, 16K context:
| Suite | Items | Accuracy |
|---|---|---|
| JevBench public | 231 | 85.7% |
| JevBench hard | 111 | 72.1% |
| DecisionBench | 586 | 75.3% |
| DecisionBench hard | 293 | 65.2% |
| This/That | 7,305 | 67.9% |
These suites also informed the choice of training data, so treat them as development results rather than a clean held-out test.
More external suites. None of their items are in the training data, but Mind2Web test shares websites with the Mind2Web train split we train on:
| Suite | Metric | Bonsai 2 27B (base) | Shingi 27B | Jev 1.13.0 (reported) |
|---|---|---|---|---|
| PubMedQA (1,000) | accuracy | 72.1% | 78.8% | 78.7% |
| SummEval relevance | Spearman | 0.563 | 0.534 | 0.526 |
| SummEval consistency | Spearman | 0.537 | 0.550 | 0.555 |
| SummEval (both) | score MAE vs experts | 0.94 | 0.51 | — |
| RewardBench | official score | 0.847 | 0.916 | — |
| Open-Jev (4,204) | accuracy | 66.7% | 85.0% | — |
| SCOTUS (640, ≤40k chars) | micro / macro-F1 | 66.1 / 57.3 | 64.4 / 56.4 | 72.6 / 62.1* |
| ECtHR A (300 cases) | micro / macro-F1 | 49.2 / 39.5 | 57.9 / 56.8 | — |
| ECtHR B (300 cases) | micro / macro-F1 | 72.5 / 72.2 | 71.1 / 68.0 | — |
| Mind2Web test | element accuracy | 85.6% | 92.4% | — |
The Jev numbers are third-party reports: PubMedQA and SummEval from Deußer et al., arXiv 2609.37647 (same 1,000 PubMedQA items; summary-level Spearman), SCOTUS from the chepyle/jev-test reanalysis. *That SCOTUS run used the full test split with truncation; ours skips the 760 longest opinions, so the two are not directly comparable.
Shingi reads images through the Bonsai 2 27B vision projector (mmproj.gguf, included
here). Send up to 8 images per request: /v1/decisions follows SGLang's decision
endpoint, and /v1/systemone takes an optional images list.
Zero-shot:
| Suite | Items | Accuracy |
|---|---|---|
| VSR (spatial yes/no) | 300 | 82.0% |
| A-OKVQA (4-way) | 300 | 89.0% |
| VQAv2 yes/no | 300 | 89.0% |
The model was not trained on images; these come from the base model's vision with Shingi's decision training on top.
Public datasets, used under their stated licenses: Banking77, CLINC150, MMLU, HelpSteer2, HelpSteer, Measuring Hate Speech, Civil Comments, GoEmotions, LEDGAR (LexGLUE), MASSIVE, CommonsenseQA, WinoGrande, GSM8K, HelpSteer3, TabFact, TAT-QA, CaseHOLD and Unfair-ToS (LexGLUE), TimeQA, Mind2Web, MedMCQA and MedQA. Several came through the jev-bench repackaging.
About a third of the training tokens are model-generated: a private synthetic dataset of decision tasks, plus the Apache-2.0 teacher data from Mapika/decider.
Apache-2.0. Derived from Bonsai 2 27B by Prism ML (Apache-2.0), which descends from Qwen3.8-27B; see NOTICE. The training datasets keep their own licenses.
11 files, 7.8 GB in total. The weights are 2 files totalling 7.8 GB in gguf.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| mmproj.gguf | Weights | 629.2 MB | 6807ede61d57 |
| shingi-27b.gguf | Weights | 7.2 GB | c62ae5b61e45 |
| calibration.json | Configuration | 2.1 KB | — |
| LICENSE | Documentation | 11.4 KB | — |
| NOTICE | Documentation | 979 B | — |
| README.md | Documentation | 7.7 KB | — |
| licenses/Bonsai-LICENSE | Documentation | 10.2 KB | — |
| assets/banner.png | Other | 5.9 MB | cc52c1310333 |
| licenses/Bonsai-NOTICE.txt | Other | 411 B | — |
| licenses/Prism-MIT | Other | 1.1 KB | — |
| .gitattributes | Repository | 1.7 KB | — |
Released by Kortexa.ai through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 7.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Yes. shingi-27b 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…