FinBERT is a pre-trained NLP model to analyze sentiment of financial text. It is built by further training the BERT language model in the finance domain, using a large financial corpus and thereby fine-tuning it for financial sentiment classification. Financial PhraseBank by Malo et al. (2014) is used for fine-tuning. For more details, please see the paper FinBERT: Financial Sentiment Analysis with Pre-trained Language Models and our related blog post on Medium. The model will give softmax outputs for three labels: positive, negative or neutral. About Prosus Prosus is a global consumer internet group and one of the largest technology investors in the world. Operating and investing globally…
Open-weight model · Text classification
laya-multilingual-coreml-ane
by Aac6fef aac6fef/laya-multilingual-coreml-ane
laya-multilingual-coreml-ane is an open-weight model for text classification from Aac6fef, released under Apache License 2.0. Its published files total 679.9 MB.
Laya typed decisions on Apple Silicon, using CPU + Neural Engine. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-multilingual. It outputs choice, score, and noul probabilities with zero generated tokens.
Parameters—
Context—
Weights645.5 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Model Card
By Aac6fef, published under apache-2.0, revision 39d6a9b3d0f6.
Laya typed decisions on Apple Silicon, using CPU + Neural Engine. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-multilingual. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-multilingual-coreml-ane", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This FP16 conversion retains the original trained parameters. The ANE graph's host…
Read Aac6fef's full model card
Laya typed decisions on Apple Silicon, using CPU + Neural Engine.
This is a portable Core ML bundle for laya-coreml,
converted from convaiinnovations/laya-multilingual.
It outputs choice, score, and noul probabilities with zero generated tokens.
Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API.
Run
Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2.
pip install laya-coreml
import laya_coreml as laya
agent = laya.load("aac6fef/laya-multilingual-coreml-ane") # Download once; Core ML runs locally.
result = agent.predict(
"The customer asks for a refund of a duplicate payment.",
{"refund": {"type": "noul", "instructions": "Does the customer request a refund?"}},
)
print(result["answers"])
To download explicitly and then run entirely offline:
hf download aac6fef/laya-multilingual-coreml-ane --local-dir models/ane
pip install 'laya-coreml[demo]'
laya-coreml-snake --model models/ane --fps 12
Use laya.load("aac6fef/laya-multilingual-coreml-ane", local_files_only=True) for a cached snapshot or pass a
local directory. Use revision="<Hub commit SHA>" to pin a remote revision.
Format and fidelity
This FP16 conversion retains the original trained parameters. The ANE graph's host action head uses FP32. Floating-point results can differ from the upstream FP32 runtime.
The fixed L96 package agrees with upstream on 59/59 fitting fixture questions and passes 100 repeated calls. Inputs longer than 96 tokens raise an error instead of being silently shortened to fit.
The exported capacity is 96 total tokens, batch 1, and 32 option slots. Questions/options and state share this budget. The ANE short exports reject over-capacity prompts. Snake uses planner features and a visible optional cycle safety shield; survival is not a claim of unaided game intelligence.
coreml_config.json records shapes, source revisions and per-file SHA256 checksums.
validation.json contains the packaging-time validation. Port fidelity on this regression
suite does not establish general task accuracy or preserved calibration on arbitrary inputs.
Performance and limits
The multilingual ANE L96 FP16 runtime measured 4.98 / 5.31 ms P50 / P95 for one short question on M3 Max; W8 measured 4.88 / 5.23 ms. Whole-system energy per decision improved 2.78× / 3.19×, respectively, against compiled MLX FP16 in that experiment. Those numbers apply to the named short ANE variants, not every bundle, long contexts, or complete Snake frames. The requested 10× improvement was not achieved.
Measurements and scope · General Core ML benchmarks · Snake demo.
Provenance
- Original checkpoint:
convaiinnovations/laya-multilingualat052592a15d198d9ad47da779604259b10b47b7aa. - Original weights SHA256:
9d628fd971b700382ac6f65920a86f149777b2e748e0c955fb3b19695aa8f204. - Upstream implementation: NandhaKishorM/laya,
commit
6a5819129eb220570792e417e49723d697efd76f. - Original models and code are by Convai Innovations and contributors, Apache-2.0.
- Independent conversion; not an official Convai Innovations or Apple release.
See LICENSE and NOTICE. Model quality and task/language limitations originate
with Laya; this runtime is an inference port, not a newly trained decision model.
Identity and Version
- Repository
- aac6fef/laya-multilingual-coreml-ane
- Publisher
- Aac6fef
- Task
- Text classification
- Modality
- Text
- Library
- coreml
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 39d6a9b3d0f67f06da74fbade6121ea134cbdb21
- First published
- 2026-09-20
- Last updated
- 2026-09-20
Files and Weights
14 files, 679.9 MB in total. The weights are 3 files totalling 645.5 MB in bin, mlmodel, safetensors.
Weights3 files · 645.5 MB
Configuration5 files · 9.5 KB
Tokenizer2 files · 34.4 MB
Documentation3 files · 15.3 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| host_weights.safetensors | Weights | 393.6 MB | 010bb264995c |
| model.mlpackage/Data/com.apple.CoreML/model.mlmodel | Weights | 1.7 MB | fb4d9cd402a1 |
| model.mlpackage/Data/com.apple.CoreML/weights/weight.bin | Weights | 250.2 MB | 09f6767a8122 |
| coreml_config.json | Configuration | 2.1 KB | — |
| encoder/config.json | Configuration | 1.9 KB | — |
| model.mlpackage/Manifest.json | Configuration | 617 B | — |
| rl_agent_config.json | Configuration | 472 B | — |
| validation.json | Configuration | 4.4 KB | — |
| LICENSE | Documentation | 10.2 KB | — |
| NOTICE | Documentation | 1.2 KB | — |
| README.md | Documentation | 4.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 609d8f4c067c |
| tokenizer/tokenizer_config.json | Tokenizer | 524 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 645.5 MB
Download from Aac6fef
Released by Aac6fef through its official repository on Hugging Face. Read the license.
Built From
- Derived from convaiinnovations/laya-multilingual
- Quantized from convaiinnovations/laya-multilingual
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 645.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About laya-multilingual-coreml-ane
Can I use laya-multilingual-coreml-ane commercially?
Yes. laya-multilingual-coreml-ane 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.
Similar Models
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.
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.
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.…
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…