StarChat Beta
StarChat Beta has model metadata, but missing tracked provider pricing keeps it from being a default production pick.
Use it for
- Teams evaluating general LLM work
- Workloads that can use a 8k context window
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- StarChat
- Released
- 2023-05-15
- Context
- 8k
- Parameters
- 16B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
No tracked provider token pricing is available yet.
About
StarChat Beta is a 16-billion parameter GPT-like large language model designed to serve as a coding assistant. It is built on the StarCoderPlus model and fine-tuned using an "uncensored" version of the openassistant-guanaco dataset, enhancing its coding capabilities but increasing the risk of generating problematic content. The model supports code generation in over 80 programming languages and facilitates conversational interactions, although it may produce biased or inaccurate outputs due to its training data. Primarily recommended for educational and research applications, users should be cautious of potential biases and content risks associated with its uncensored training data.
StarChat Beta is an open-source model in the StarChat family. The structured metadata tracks a 8k-token context window. No headline benchmark score is tracked for StarChat Beta yet.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.