LLM Reference

StarChat Models by Hugging Face H4

Hugging Face H4BigCode OpenRAIL-MOpen weights
2 models2023Up to 8k ctx

Details

ResearcherHugging Face H4
Commercial useCommercial use: conditional
Models2
Released2023
Max context8k

About

StarChat is a family of 2 AI models by Hugging Face H4, released in 2023.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs 8k context and 16B parameters.

2023-058k context16B parameters

Use when the workload needs 8k context and 16B parameters.

2023-058k context16B parameters

Release Timeline

1 release group
2023-05
2 current
StarChat Alpha
8k context16B parameters
Current
StarChat Beta
8k context16B parameters
Current

Specifications(2 models)

StarChat model specifications comparison
ModelReleasedContextParameters
StarChat Alpha2023-058k16B
StarChat Beta2023-058k16B

Frequently Asked Questions

What is StarChat used for?
StarChat is used for coding. The family description and listed model capabilities point to those workloads as the best fit.
How does StarChat compare to Zephyr?
StarChat by Hugging Face H4 is strongest where you need coding, while Zephyr by Hugging Face H4 is the closest related family to check for structured outputs. StarChat has 2 listed variants and reaches up to 8k context, while Zephyr reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
Which StarChat model should I use?
If price is the main constraint, use the pricing table first because StarChat does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate StarChat Alpha with 8k context.