Promote Sign in Sign up

Text model

Schematron 3B

3B long-context HTML-to-JSON extraction model tuned for fast, cheap structured extraction on standard web pages, matching frontier accuracy for many tasks while keeping the same 128K context and strict JSON mode.

Inference Text Open weights llama3.2
Open model card ↗
Type
Text
Weights
Open
Downloads
814
Likes
343
Pipeline
text generation
License
llama3.2

Model hub

inference-net/Schematron-3B

Repo
inference-net/Schematron-3B
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors llama text-generation conversational base_model:meta-llama/Llama-3.2-3B-Instruct base_model:finetune:meta-llama/Llama-3.2-3B-Instruct text-generation-inference endpoints_compatible
Open on Hugging Face

More from Inference

1

About Inference

1

There is less of a GPU shortage than you have been led to believe. Data centers have underutilized capacity, but it comes in a form that most orchestration software is not capable of using: a few minutes here, a few hours there.