Our great sponsors
-
The onnxruntime gem already contains binary files for each platform, so you don't need to install the ONNX runtime yourself. Just install the gem and it should work.
-
The tokenizers gem is written in Rust, so installation requires Rust. If Rust isn't available, blingfire can be used instead.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
numo-narray - Ruby matrix library. Equivalent to NumPy.
-
The tokenizers gem is written in Rust, so installation requires Rust. If Rust isn't available, blingfire can be used instead.
-
The tokenizers gem is written in Rust, so installation requires Rust. If Rust isn't available, blingfire can be used instead.
-
Here we use the GPT-2 model distributed by the ONNX official. Download GPT-2-LM-HEAD from the link.
-
Put gpt2-lm-head-10.onnx in the same directory as the script. You can browse the content of ONNX models using NETRON.
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
Related posts
- Operationalize TensorFlow Models With ML.NET
- Has anyone successfully converted an onnx model to tensorflow? Here's the problems I'm having...
- AI Inference now available in Supabase Edge Functions
- Tinygrad: Hacked 4090 driver to enable P2P
- Functions and operators for Dot and Matrix multiplication and Element-wise calculation in PyTorch