Commit
•
e4909bc
1
Parent(s):
9338c8b
Update README.md
Browse files
README.md
CHANGED
|
@@ -69,6 +69,14 @@ Quatizations provided by [TheBloke](https://huggingface.co/TheBloke/laser-dolphi
|
|
| 69 |
+ GGUF chat available [here](https://huggingface.co/spaces/macadeliccc/laser-dolphin-mixtral-chat-GGUF)
|
| 70 |
+ 4-bit bnb chat available [here](https://huggingface.co/spaces/macadeliccc/laser-dolphin-mixtral-chat)
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
## Code Example
|
| 73 |
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
|
| 74 |
|
|
|
|
| 69 |
+ GGUF chat available [here](https://huggingface.co/spaces/macadeliccc/laser-dolphin-mixtral-chat-GGUF)
|
| 70 |
+ 4-bit bnb chat available [here](https://huggingface.co/spaces/macadeliccc/laser-dolphin-mixtral-chat)
|
| 71 |
|
| 72 |
+
# Ollama
|
| 73 |
+
|
| 74 |
+
```bash
|
| 75 |
+
ollama run macadeliccc/laser-dolphin-mixtral-2x7b-dpo
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
|
| 80 |
## Code Example
|
| 81 |
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
|
| 82 |
|