Palmyra 20B
Palmyra 20B 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 2k 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
- Palmyra
- Released
- 2023-03-02
- Context
- 2k
- Parameters
- 20B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
About
The Palmyra 20B model is a causal decoder-only large language model developed by Writer, equipped with 20 billion parameters. Noted for its speed, the model excels in tasks such as sentiment classification and summarization, although it should be used cautiously as it may not always ensure factual accuracy. Primarily focused on English, it demonstrates some capabilities in languages like German, Spanish, French, and Swedish. However, it is no longer actively maintained, and its use in critical applications is discouraged. The model serves as a foundation for others, including the InstructPalmyra-20b, which is fine-tuned for instruction-following tasks. It is available on Hugging Face and compatible with tools like AutoModelForCausalLM and text-generation-inference. Users should be mindful of potential biases inherent in its training data.
Palmyra 20B is a model in the Palmyra family. The structured metadata tracks a 2k-token context window. No headline benchmark score is tracked for Palmyra 20B 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.