|
--- |
|
base_model: mistralai/Mistral-Nemo-Base-2407 |
|
license: apache-2.0 |
|
datasets: |
|
- BeaverAI/Nemo-Inst-Tune-ds |
|
language: |
|
- en |
|
library_name: transformers |
|
--- |
|
This is an ExLlamaV2 quantized model in 3.5bpw of [BeaverAI/mistral-dory-12b](https://huggingface.co/BeaverAI/mistral-dory-12b) using the default calibration dataset with 8192 context length. |
|
|
|
# Original Model card: |
|
|
|
# Dory 12b |
|
redone instruct finetune of mistral nemo 12b. *not* (E)RP-focused, leave that to drummer. |
|
|
|
![image/gif](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/tP5kiebGrg8DJZbeBEc3Q.gif) |
|
|
|
thanks to twisted for the compute :3 |
|
|
|
## Prompting |
|
alpaca-like: |
|
``` |
|
### System: |
|
[Optional system prompt] |
|
|
|
### Instruction: |
|
[Query] |
|
|
|
### Response: |
|
[Response]<EOT> |
|
|
|
### Instruction: |
|
[...] |
|
``` |
|
|
|
## Training details |
|
Rank 64 QDoRA, trained on primarily Claude and Gemma 2 multiturn data (it's midnight and I'll probably write more details tomorrow) |