Stable LM 2 Chat 1.6B
Stable LM 2 Chat 1.6B is an English instruction-tuned version of the 1.6B base. Its training combines public and synthetic instruction data with Direct Preference Optimization.
Research release
Model design and access
The card lists instruction, mathematical and preference datasets. This Chat release is distinct from the earlier Zephyr 1.6B checkpoint. It is intended for conversational use, but its published license should not be replaced with the Community License of the base model.Stable LM 2 Chat 1.6B official model card
Practical use
Practical guidance. Use the checkpoint's chat template when evaluating local dialogue. Small-model fluency can hide incorrect details, so assess the exact question types and output formats the application needs. Keep its research terms visible when comparing it with compact models that permit broader commercial deployment.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | stablelm-2-1_6b-chat |
| Context window | 4,096 tokens Published checkpoint sequence length; prompt and generated text share the window. Stable LM 2 Chat 1.6B configuration |
| Base | Stable LM 2 1.6B.Stable LM 2 Chat 1.6B official model card |
| Prompt format | ChatML.Stable LM 2 Chat 1.6B official model card |
| License | Non-Commercial Research Community License; separate commercial agreement required.Stable LM 2 Chat 1.6B official model card |
Related models
- Stable LM 2 1.6B
Stability AI · Stable LM
A 1.6B base language model pretrained on multilingual text and code.
Launch date not confirmedDownloadable - Stable LM 2 Chat 12B
Stability AI · Stable LM
Stable LM 2 Chat 12B is an English instruction-tuned model with documented function calling.
Launch date not confirmedResearch releaseDownloadable - Stable LM 2 Zephyr 1.6B
Stability AI · Stable LM
Stable LM 2 Zephyr 1.6B is an earlier instruction-tuned release based on Stable LM 2 1.6B.
Launch date not confirmedResearch releaseDownloadable