README.md

---
base_model: mistralai/Mistral-Nemo-Base-2407
license: apache-2.0
datasets:
- BeaverAI/Nemo-Inst-Tune-ds
language:
- en
library_name: transformers
---
# Dory 12b (v2)
(redone) redone instruct finetune of mistral nemo 12b's base. *not* (E)RP-focused, leave that to drummer.

![image/gif](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/BiBtgV_WEIha72WqETWfk.gif)

thanks to twisted again for the compute :3

## Prompting
alpaca-like:
```
### System:
[Optional system prompt]

### Instruction:
[Query]

### Response:
[Response]</s>

### Instruction:
[...]
```

## Training details
Rank 64 QDoRA, trained on the following data mix:
- All of [kalomaze/Opus_Instruct_3k](https://huggingface.co./datasets/kalomaze/Opus_Instruct_3k)
- All conversations with a reward model rating above 5 in [Magpie-Align/Magpie-Gemma2-Pro-Preview-Filtered](https://huggingface.co./datasets/Magpie-Align/Magpie-Gemma2-Pro-Preview-Filtered)
- 50k of [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co./datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned)
- All stories above 4.7 rating and published before 2020 in [Fizzarolli/FallingThroughTheSkies-592k-Filtered-Filtered](https://huggingface.co./datasets/Fizzarolli/FallingThroughTheSkies-592k-Filtered-Filtered)