# LongReward Llama3.1 8B DPO

LongReward Llama3.1 8B DPO is a model from Z.ai with open weights, first recorded on 30 Sep 2026; its release date is not established.

- Developer: Z.ai
- Id: zai-org/LongReward-llama3.1-8b-DPO
- Sighting: 2026-09-30T15:57:05.629Z
  - [evidence link](https://huggingface.co/zai-org/LongReward-llama3.1-8b-DPO)
- Status: Released
- Weights version: 2024-10-22
  - [evidence link](https://huggingface.co/api/models/zai-org/LongReward-llama3.1-8b-DPO/paths-info/7311e4ca36e3ef3649c1d358063bd370fb1212c4)
- Canonical: https://alexgetman.com/models/z-ai/longreward-llama3-1-8b-dpo/

## Questions

### Are the weights of LongReward Llama3.1 8B DPO publicly available?

Yes. Z.ai publishes the weights.

### When was LongReward Llama3.1 8B DPO released?

Its release date is not established. Signal Forge first recorded it on 30 Sep 2026.

## Evidence links

- [hf-author-artifacts:zai-org](https://huggingface.co/api/models/zai-org/LongReward-llama3.1-8b-DPO/paths-info/7311e4ca36e3ef3649c1d358063bd370fb1212c4)
- [huggingface:zai-org](https://huggingface.co/zai-org/LongReward-llama3.1-8b-DPO)

## Signals