Commit
•
81d3858
1
Parent(s):
c79eb93
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,12 @@ V2 has improvements in all areas from V1; it's not a massive improvement, but I
|
|
| 18 |
|
| 19 |
I really like the model selection in this one, so I don't know how much more I can improve if I make another 4x8B merge. If I were to make a V3, swapping Meta-Llama-3-8B-Instruct would likely be the only change. I will try my hand at making an 8x8B merge in the future, but I still need to find some models to fill the gaps; making sure there's no routing conflicts between 8 different models at once will be the biggest challenge.
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
# Details
|
| 23 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|
|
|
|
| 18 |
|
| 19 |
I really like the model selection in this one, so I don't know how much more I can improve if I make another 4x8B merge. If I were to make a V3, swapping Meta-Llama-3-8B-Instruct would likely be the only change. I will try my hand at making an 8x8B merge in the future, but I still need to find some models to fill the gaps; making sure there's no routing conflicts between 8 different models at once will be the biggest challenge.
|
| 20 |
|
| 21 |
+
# Quantization Formats
|
| 22 |
+
**GGUF**
|
| 23 |
+
- Static:
|
| 24 |
+
- https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-GGUF
|
| 25 |
+
- Imatrix:
|
| 26 |
+
- https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF
|
| 27 |
|
| 28 |
# Details
|
| 29 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|