InternLM Models by Intern-AI
About
The InternLM family is a collection of open-source large language models developed by the Shanghai AI Laboratory, available in parameter sizes of 1.8B, 7B, and 20B. These models are designed for practical use and are trained on trillions of high-quality tokens, endowing them with a comprehensive knowledge base. They feature support for long context windows, up to 1 million tokens in some versions, and offer enhanced reasoning capabilities, particularly in mathematics, along with improved tool usage. The range includes specialized models like InternLM-XComposer, which excels in tasks involving text-image comprehension and composition. These models are accessible on platforms like Hugging Face and ModelScope, with the code released under the Apache-2.0 license 313.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 4k context and 20B parameters.
Use when the workload needs 4k context and 7B parameters.
Use when the workload needs 4k context and 7 parameters.
Use when the workload needs 4k context and 13 parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| InternLM 20B | Use when the workload needs 4k context and 20B parameters. | 2023-07 | 4k context20B parameters | Current |
| InternLM 7B | Use when the workload needs 4k context and 7B parameters. | 2023-07 | 4k context7B parameters | Current |
| InternLM | Use when the workload needs 4k context and 7 parameters. | 2023-06 | 4k context7 parameters | Current |
| InternLM 13B | Use when the workload needs 4k context and 13 parameters. | 2023-06 | 4k context13 parameters | Current |
Release Timeline
2 release groupsSpecifications(4 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| InternLM 20B | 2023-07 | 4k | 20B |
| InternLM 7B | 2023-07 | 4k | 7B |
| InternLM | 2023-06 | 4k | 7 |
| InternLM 13B | 2023-06 | 4k | 13 |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| InternLM 7B | Bitdeer AI | $0.14 | $0.42 | Serverless |
| InternLM 20B | Bitdeer AI | $0.14 | $0.42 | Serverless |
Frequently Asked Questions
- What is InternLM used for?
- InternLM is used for coding and math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.
- How does InternLM compare to InternVL?
- InternLM by Intern-AI is strongest where you need coding, while InternVL by Intern-AI is the closest related family to check for adjacent model selection. InternLM has 4 listed variants and reaches up to 4k context, while InternVL reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
- Which InternLM model should I use?
- For the lowest listed input price, start with InternLM 7B through Bitdeer AI at $0.14/1M input tokens. For the most capable/latest local choice, evaluate InternLM 20B with 4k context.
