Platypus2 Models by garage-bAInd
About
The Platypus2 family of large language models (LLMs) stands out for its impressive performance on the HuggingFace Open LLM Leaderboard. Developed by Boston University, these models utilize the LLaMA-2 transformer architecture and leverage a specialized dataset named Open-Platypus, emphasizing STEM and logical reasoning. Through sophisticated fine-tuning techniques like Low-Rank Adaptation (LoRA) and Parameter-Efficient Fine-Tuning (PEFT), Platypus2 achieves remarkable results with reduced training data and computational demands compared to its peers. Available in various quantized formats, such as GGUF, these models offer efficient inference across diverse hardware platforms. While excelling in English, caution is advised regarding their application in other languages and safety protocols prior to deployment. Notably, the 13B parameter version has been further enhanced by merging with models like OpenOrca to amplify its abilities 136.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 70B parameters and structured outputs.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Platypus2 70B | Use when the workload needs 70B parameters and structured outputs. | 2023-12 | 70B parametersstructured outputs | Current |
| Platypus2 13B | Use when the workload needs 13B parameters. | 2023-12 | 13B parameters | Current |
| Platypus2 7B | Use when the workload needs 7B parameters. | 2023-12 | 7B parameters | Current |
Release Timeline
1 release groupSpecifications(3 models)
| Model | Released | Parameters | Structured Outputs |
|---|---|---|---|
| Platypus2 70B | 2023-12 | 70B | Yes |
| Platypus2 13B | 2023-12 | 13B | No |
| Platypus2 7B | 2023-12 | 7B | No |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Platypus2 70B | Together AI | $0.9 | $0.9 | Serverless |
Frequently Asked Questions
- What is Platypus2 used for?
- Platypus2 is used for structured outputs and coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Platypus2 compare to Platypus?
- Platypus2 by garage-bAInd is strongest where you need structured outputs, while Platypus by garage-bAInd is the closest related family to check for adjacent model selection. Platypus2 has 3 listed variants, while Platypus reaches up to 2k context, so compare the specs and pricing tables before choosing a production model.
- Which Platypus2 model should I use?
- For the lowest listed input price, start with Platypus2 70B through Together AI at $0.9/1M input tokens. For the most capable/latest local choice, evaluate Platypus2 70B with structured outputs.
