Japanese StableLM Models by Stability AI
About
The Japanese StableLM family, developed by Stability AI, focuses on Japanese language processing, providing advanced AI capabilities tailored for Japanese speakers. These large language models (LLMs) excel in text generation tasks and offer both general-purpose and instruction-tuned variants with diverse parameter sizes, catering to different performance and resource needs. Early models, such as Japanese StableLM Alpha, showcased superior performance in benchmarks against other Japanese LLMs. Subsequent versions, like the Japanese StableLM Beta series, enhanced the foundational Llama 2 architecture by incorporating additional training data, improving Japanese language proficiency and culturally specific knowledge. These models are accessible on Hugging Face and come with various licenses supporting research and commercial applications 412.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 4k context and 70B parameters.
Use when the workload needs 4k context and 7B parameters.
Use when the workload needs 4k context and 3B parameters.
Use when the workload needs 8k context and 7B parameters.
Use when the workload needs 2k context and 7B parameters.
Use when the workload needs 4k context and 7B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Japanese StableLM 70B | Use when the workload needs 4k context and 70B parameters. | 2023-04 | 4k context70B parameters | Current |
| Japanese StableLM 7B | Use when the workload needs 4k context and 7B parameters. | 2023-04 | 4k context7B parameters | Current |
| Japanese StableLM 3B | Use when the workload needs 4k context and 3B parameters. | 2023-04 | 4k context3B parameters | Current |
| Japanese StableLM Gamma 7B | Use when the workload needs 8k context and 7B parameters. | 2023-04 | 8k context7B parameters | Current |
| Japanese StableLM Alpha 7B | Use when the workload needs 2k context and 7B parameters. | 2023-04 | 2k context7B parameters | Current |
| Japanese Stable VLM | Use when the workload needs 7B parameters. | 2023-04 | 7B parameters | Current |
| Japanese StableLM Beta 7B | Use when the workload needs 4k context and 7B parameters. | 2023-04 | 4k context7B parameters | Current |
Release Timeline
1 release groupSpecifications(7 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Japanese StableLM 70B | 2023-04 | 4k | 70B |
| Japanese StableLM 7B | 2023-04 | 4k | 7B |
| Japanese StableLM 3B | 2023-04 | 4k | 3B |
| Japanese StableLM Gamma 7B | 2023-04 | 8k | 7B |
| Japanese StableLM Alpha 7B | 2023-04 | 2k | 7B |
| Japanese Stable VLM | 2023-04 | — | 7B |
| Japanese StableLM Beta 7B | 2023-04 | 4k | 7B |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Japanese StableLM Gamma 7B | Fireworks AI | $0.2 | $0.2 | Provisioned |
| Japanese Stable VLM | Fireworks AI | $0.2 | $0.2 | Provisioned |
| Japanese StableLM 70B | Fireworks AI | $0.9 | $0.9 | Provisioned |
Frequently Asked Questions
- What is Japanese StableLM used for?
- Japanese StableLM is used for coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Japanese StableLM compare to Stable Virtual Assistant?
- Japanese StableLM by Stability AI is strongest where you need coding, while Stable Virtual Assistant by Stability AI is the closest related family to check for adjacent model selection. Japanese StableLM has 7 listed variants and reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
- Which Japanese StableLM model should I use?
- For the lowest listed input price, start with Japanese StableLM Gamma 7B through Fireworks AI at $0.2/1M input tokens. For the most capable/latest local choice, evaluate Japanese StableLM Gamma 7B with 8k context.
