general tensor
We're a team of ml engineers (x-google, x-apple) based in san francisco. We've develop small, specialized models that do exceptionally well at specific tasks that large, general-purpose models suck at. Tasks that demand precision, speed, and reliability over broad capabilities.
List of our models:
pii-redactor-general-V2
securityA compact vlm combined with rules to identify and de-identify personally identifiable information in text and images
code-diff-merge-V2
codeFast and accurate small language model for applying code diffs
signature-detect-V1
contentVision model to identify and verify handwritten signatures in images
toxic-guard-text-V1
safetyReal-time detection of harmful language and content in text
toxic-guard-image-V1
safetyReal-time detection of harmful language and content in images
embedding-base-V1.5
batchHigh-throughput multi-modal encoder for large-scale processing
logo-locator-V0.1
contentVision model to detect and locate logos in images
jailbreak-guard-V1
securityProtection against prompt injection and jailbreak attempts
voice-detect-V1
audioSmall audio model for turn detection and speaker verification
prompt-injection-shield-V1.1
securityReal-time detection and prevention of prompt injection attacks with a classifier powered by a database of embeddings
nsfw-image-classifier-V1
safetyImage classifier for not-safe-for-work content
financial-sense-V0.1
safetyText classifier for detection of sensitive financial content (e.g. financial advice) in text and images
ocr-table-extract-V1
contentCompact multimodal model for extracting tabular data embedded in scanned documents and pdfs
text-autocomplete-V1
contentSmall language model for fast, accurate context-aware text completions
tts-alignment-V1
audioPrecise text-to-speech timing and phoneme alignment
typo-correction-V1
contentTiny language model for spelling and grammar correction
noise-suppression-V0.2
audioReal-time noise reduction and cleanup for noisy audio
embeddings-text-log-V0.1
codeEmbeddings for log analysis and search
pipe-sql-V0.2
codeSmall language model to convert NL queries to SQL statements
object-tracking-video-V0.2
contentTrack custom objects in video
pii-redactor-name-V1
securitySmall language model to identify and de-identify names in text
What makes our models different:
- Task-optimized: each model is built for one thing, does it exceptionally well
- Fast: 5-100x faster inference than general models
- Cost-efficient: also radically cheaper
- Lightweight and flexible deployment: simple API access or runnable on edge hardware -- no torch or other bulky dependencies
- Safe and performant: we regularly review, audit, and benchmark all models for continuous improvement
contact
We're currently in private beta. Contact us if you're interested in using our models.