Orca 13B
Orca 13B 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
- Orca
- Released
- 2023-06-05
- Context
- 2k
- Parameters
- 13B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
Advancing the state-of-the-art in AI and computing.
No tracked provider token pricing is available yet.
About
Orca 13B, a powerful AI language model developed by Microsoft, leverages a fine-tuned LLaMA-2 base model architecture to mimic the reasoning processes of larger models like GPT-4. Although significantly smaller than GPT-4, it requires fewer computational resources and aims for comparable performance. The model enhances reasoning abilities using a synthetic training dataset moderated by Microsoft Azure content filters. Its capabilities include reasoning, reading comprehension, math problem-solving, and text summarization, though it's not optimized for chat tasks. Orca 13B employs a progressive learning approach, learning from GPT-4's explanation traces to improve accuracy and contextual understanding. However, it may still exhibit biases, hallucinate, and misinterpret scenarios. Different quantized versions are available, offering various trade-offs in speed, accuracy, and memory usage.
Orca 13B is a model in the Orca family. The structured metadata tracks a 2k-token context window. No headline benchmark score is tracked for Orca 13B 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.