The request names deberta-small-long-nli, a model. None of the candidate products is that model or its model hub entry in the sources shown; the closest are Hugging Face Hub, which hosts pretrained models 717, and Sentence Transformers, which uses and trains embedding and reranker models 2. Note that the Hugging Face Hub entry is the place to get the named model itself, and the sources do not confirm that it hosts this specific checkpoint.
- 1
Hugging Face Hubhuggingface.coverified and signed
The huggingface_hub Python library lets you interact with the Hub to discover pre-trained models and share your own, which is where a named checkpoint like deberta-small-long-nli is normally found.
official:SDK · huggingface-hub
for agents: models · model-hub · pretrained-models
- 2
Sentence Transformerssbert.netverified and signed
Sentence Transformers (SBERT) is a Python module for using and training state-of-the-art embedding and reranker models, a related option for NLI-style cross-encoder work.
official:SDK · sentence-transformers+24 community tools built for it
for agents: XLNet · deep · BERT
- 3
Replicatereplicate.comverified and signed
Replicate runs open-source machine learning models through a cloud API, an alternative if you want to call a hosted model rather than load it locally.
for agents: ibm-granite/granite-4.0-h-small
Sources
- 2SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
- 7🤗 Hub client library · Hugging Facehuggingface.co · read 2026-10-29
- 9Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 17huggingface-hub: declares "models" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
XLNet · sentence-transformers verified and signed
database · snowflake-sqlalchemy verified and signed
test · pytest verified and signed
pydantic · pydantic verified and signed
Pydantic is a Python data validation and serialization library, based on type hints. Use this skill whenever you need to do relatively complex data modeling using Pydantic, e.g. when adding constraints, defining a model hierarchy with subclasses, etc.
· ONNX website read, tools not yet checked
models · huggingface-hub verified and signed
· SGLang website read, tools not yet checked
SGLang powers fast, scalable inference for large language and multimodal models. Open-source serving framework with state-of-the-art performance.
ibm-granite/granite-4.0-h-small · ibm-granite/granite-4.0-h-small verified and signed
Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
build-models · build-models verified and signed
Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace,
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.