MetaMath 13B
MetaMath 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
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
- MetaMath
- Released
- 2023-10-27
- Parameters
- 13B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
About
MetaMath 13B is a specialized large language model fine-tuned for mathematical reasoning, built upon the LLaMA-7B architecture. It significantly enhances mathematical problem-solving by leveraging the MetaMathQA dataset, which includes augmented content from existing datasets like GSM8K and MATH. This model excels in benchmark tests, outperforming many open-source models of similar size, although it falls short compared to some closed-source models like GPT-3.5-Turbo. While the MetaMathQA dataset is available to the public, the details of its creation and fine-tuning are not fully transparent. MetaMath 13B's proficiency is notably strong in mathematical domains, but less so elsewhere, with performance varying based on question complexity and phrasing. Available in quantized formats like GPTQ and AWQ, it supports various inference tools, offering flexibility in resource usage.
MetaMath 13B is a model in the MetaMath family. No headline benchmark score is tracked for MetaMath 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.