Commit
•
a75d8a6
1
Parent(s):
dbddb2d
Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,10 @@ Quatizations provided by [TheBloke](https://huggingface.co/TheBloke/laser-dolphi
|
|
| 34 |
*Current [Quantizations](https://huggingface.co/macadeliccc/laser-dolphin-mixtral-2x7b-GGUF)*
|
| 35 |
- Q4_K_M
|
| 36 |
- Q5_K_M
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
| 38 |
## Code Example
|
| 39 |
Switch the commented model definition to use in 4-bit. Should work with 9GB and still exceed the single 7B model by 5-6 points roughly
|
| 40 |
|
|
|
|
| 34 |
*Current [Quantizations](https://huggingface.co/macadeliccc/laser-dolphin-mixtral-2x7b-GGUF)*
|
| 35 |
- Q4_K_M
|
| 36 |
- Q5_K_M
|
| 37 |
+
|
| 38 |
+
GGUF chat available [here](https://huggingface.co/spaces/macadeliccc/laser-dolphin-mixtral-chat-GGUF)
|
| 39 |
+
4-bit bnb chat available [here](https://huggingface.co/spaces/macadeliccc/laser-dolphin-mixtral-chat)
|
| 40 |
+
|
| 41 |
## Code Example
|
| 42 |
Switch the commented model definition to use in 4-bit. Should work with 9GB and still exceed the single 7B model by 5-6 points roughly
|
| 43 |
|