DeciCoder Models by Deci AI
About
The DeciCoder family consists of open-source large language models (LLMs) focused on code generation, developed by Deci AI. These models leverage Deci's proprietary AutoNAC technology to optimize their architecture for enhanced accuracy and speed 52. The flagship model, DeciCoder-1b, features 1 billion parameters and is specifically designed for code completion tasks. Trained on subsets of the Starcoder Training Dataset, it supports languages like Python, Java, and JavaScript and is equipped with Grouped Query Attention and a 2048-token context window 2. Designed to efficiently generate accurate code, DeciCoder models offer cost savings by running effectively on more affordable hardware, with plans for expanding the model lineup 53.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 4k context and 6B parameters.
Use when the workload needs 4k context and 1B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| DeciCoder 6B | Use when the workload needs 4k context and 6B parameters. | 2023-08 | 4k context6B parameters | Current |
| DeciCoder 1B | Use when the workload needs 4k context and 1B parameters. | 2023-08 | 4k context1B parameters | Current |
Release Timeline
1 release groupSpecifications(2 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| DeciCoder 6B | 2023-08 | 4k | 6B |
| DeciCoder 1B | 2023-08 | 4k | 1B |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| DeciCoder 1B | Microsoft Foundry | $0.07 | $0.07 | Provisioned |
Frequently Asked Questions
- What is DeciCoder used for?
- DeciCoder is used for coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does DeciCoder compare to DeciLM?
- DeciCoder by Deci AI is strongest where you need coding, while DeciLM by Deci AI is the closest related family to check for coding. DeciCoder has 2 listed variants and reaches up to 4k context, while DeciLM reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
- Which DeciCoder model should I use?
- For the lowest listed input price, start with DeciCoder 1B through Microsoft Foundry at $0.07/1M input tokens. For the most capable/latest local choice, evaluate DeciCoder 6B with 4k context.
