Commit
·
8b7b50f
1
Parent(s):
dfc9c79
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,9 @@ license: bigcode-openrail-m
|
|
| 16 |
- Finetuning was performed using QLoRa on a single RTX6000 48GB.
|
| 17 |
- If you want just the QLoRa/LoRA adapter: [richardr1126/qlora-spider-natsql-wizard-coder-adapt](https://huggingface.co/richardr1126/qlora-spider-natsql-wizard-coder-adapter)
|
| 18 |
|
|
|
|
|
|
|
|
|
|
| 19 |
## Citation
|
| 20 |
|
| 21 |
Please cite the repo if you use the data or code in this repo.
|
|
|
|
| 16 |
- Finetuning was performed using QLoRa on a single RTX6000 48GB.
|
| 17 |
- If you want just the QLoRa/LoRA adapter: [richardr1126/qlora-spider-natsql-wizard-coder-adapt](https://huggingface.co/richardr1126/qlora-spider-natsql-wizard-coder-adapter)
|
| 18 |
|
| 19 |
+
### Running the GGML model
|
| 20 |
+
- The best way to run this model is to use the [GGML version](https://huggingface.co/richardr1126/qlora-spider-natsql-wizard-coder-adapter) on [koboldcpp](https://github.com/LostRuins/koboldcpp), with CuBlas support.
|
| 21 |
+
|
| 22 |
## Citation
|
| 23 |
|
| 24 |
Please cite the repo if you use the data or code in this repo.
|