LingoWhale Models by DeepLang AI
About
The LingoWhale family of large language models (LLMs) is developed by DeepLangAI in collaboration with THUNLP Lab. This series includes LingoWhale-8B, a bilingual model pre-trained on a substantial volume of high-quality Chinese-English data 1. With an 8K context window, it excels in comprehending and generating longer sequences. The model is open-source for academic research, though commercial use requires prior approval 1. LingoWhale-8B achieves high performance on public benchmarks but faces challenges such as hallucinations and weaker mathematical capabilities. Subsequent versions aim to overcome these limitations, with support provided through model weights, a Huggingface inference interface, and parameter-efficient fine-tuning examples like LoRA 1.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 4k context and 8B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| LingoWhale 8B | Use when the workload needs 4k context and 8B parameters. | 2024-09 | 4k context8B parameters | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| LingoWhale 8B | 2024-09 | 4k | 8B |
Frequently Asked Questions
- What is LingoWhale used for?
- LingoWhale is used for math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.
- How does LingoWhale compare to Claude 3?
- LingoWhale by DeepLang AI is strongest where you need math-heavy prompts, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. LingoWhale has 1 listed variant and reaches up to 4k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which LingoWhale model should I use?
- If price is the main constraint, use the pricing table first because LingoWhale does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate LingoWhale 8B with 4k context.