Commit
•
132adbe
1
Parent(s):
3485890
Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,11 @@ Likewise, I have found that censorship does not come from the model's weights bu
|
|
| 22 |
|
| 23 |
I have tried using over a dozen different models as the base, and Synthia is by far the best. Aside from swapping in better models, the only way that I can see to improve from here is to merge Synthia with other models in order to reduce these shortcomings, which I will definitely be doing in the future.
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
# Details
|
| 26 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|
| 27 |
- **Instruct Format**: [llama-3](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/)
|
|
|
|
| 22 |
|
| 23 |
I have tried using over a dozen different models as the base, and Synthia is by far the best. Aside from swapping in better models, the only way that I can see to improve from here is to merge Synthia with other models in order to reduce these shortcomings, which I will definitely be doing in the future.
|
| 24 |
|
| 25 |
+
# Quantization Formats
|
| 26 |
+
**GGUF**
|
| 27 |
+
- Static:
|
| 28 |
+
- https://huggingface.co/bartowski/Llama-Salad-8x8B-GGUF
|
| 29 |
+
|
| 30 |
# Details
|
| 31 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|
| 32 |
- **Instruct Format**: [llama-3](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/)
|