Palmyra Med 20B
Palmyra Med 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
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 Med
- Released
- 2023-08-02
- Parameters
- 20B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
About
Palmyra-Med-20b, a large language model with 20 billion parameters, is tailored for medical applications, developed by Writer. It is a causal decoder-only model, which sequentially predicts text, and has been fine-tuned using a custom-curated dataset that blends PubMedQA and MedQA data. This setup aims to improve performance in medical dialogues and question-answering tasks. The model's capabilities extend to answering complex medical questions, engaging in dialogues, and potentially aiding in clinical decision-making and research. Despite these features, Palmyra-Med-20b is deprecated and no longer maintained. Consequently, its creators advise against its use in production, recommending newer models instead. The model primarily operates in English, may exhibit biases inherent in its training data, and requires a single 40GB A100 GPU for operation.
Palmyra Med 20B is a model in the Palmyra Med family. No headline benchmark score is tracked for Palmyra Med 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.