dolphin-mistral:7b-v2.8-q3_K_L

標籤	日期	筆記
`v2.8` `latest`	03/31/2024	基於 Mistral 0.2，支援 32K tokens 的上下文視窗。
`v2.6`	12/27/2023	修復了訓練配置問題，提升了品質，並改進了用於同理心的訓練資料集。
`v2.2.1`	10/30/2023	這是檢查點版本，用於修復過度擬合訓練
`v2.2`	10/29/2023	新增了對話和同理心資料。
`v2.1`	10/11/2023	使用 airoboros 資料集增強。
`v2.0`	10/2/2023	模型的初始版本。

參考資料

HuggingFace

The Dolphin model by Eric Hartford, based on [Mistral](https://ollama.dev.org.tw/library/mistral) version 0.2 released in March 2024. This model is uncensored, available for both commercial and non-commercial use, and excels at coding.

## Versions
| Tag             | Date       | Notes                                                                                                             |
| --------------- | ---------- | ----------------------------------------------------------------------------------------------------------------- |
| `v2.8` `latest` | 03/31/2024 | Based on Mistral 0.2 with support for a context window of 32K tokens.                                             |
| `v2.6`          | 12/27/2023 | Fixed a training configuration issue that improved quality, and improvements to the training dataset for empathy. |
| `v2.2.1`        | 10/30/2023 | This is a checkpoint release, to fix overfit training                                                             |
| `v2.2`          | 10/29/2023 | Added conversation and empathy data.                                                                              |
| `v2.1`          | 10/11/2023 | Enhanced with the airoboros dataset.                                                                              |
| `v2.0`          | 10/2/2023  | Initial release of the model.                                                                                     |

## References

[HuggingFace](https://huggingface.co/cognitivecomputations)

貼上、拖曳或點擊以上傳圖片 (.png, .jpeg, .jpg, .svg, .gif)