Commit
•
d5f0e65
1
Parent(s):
b51d891
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,9 @@ While role-play was the main focus of this merge, its base capabilities weren't
|
|
| 17 |
|
| 18 |
Unfortunately, I can't compare it with 70B models because they're too slow on my machine, but this is the best sub-70B model I have used so far; I haven't felt the need to regenerate any responses, which hasn't happened with any other model so far. This is my first attempt at any kind of merge, and I want to share what I've learned, but this section is already longer than I wanted, so I've decided to place the rest at the bottom of the page.
|
| 19 |
|
|
|
|
|
|
|
|
|
|
| 20 |
# Details
|
| 21 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|
| 22 |
- **Instruct Format**: [llama-3](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/)
|
|
|
|
| 17 |
|
| 18 |
Unfortunately, I can't compare it with 70B models because they're too slow on my machine, but this is the best sub-70B model I have used so far; I haven't felt the need to regenerate any responses, which hasn't happened with any other model so far. This is my first attempt at any kind of merge, and I want to share what I've learned, but this section is already longer than I wanted, so I've decided to place the rest at the bottom of the page.
|
| 19 |
|
| 20 |
+
# Quantization Formats
|
| 21 |
+
- **GGUF**: https://huggingface.co/HiroseKoichi/Llama-Salad-4x8B-GGUF
|
| 22 |
+
|
| 23 |
# Details
|
| 24 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|
| 25 |
- **Instruct Format**: [llama-3](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/)
|