Update README.md
Browse files
README.md
CHANGED
|
@@ -62,6 +62,14 @@ Experimentally we note that Mistral-24B based models require a low temperature.
|
|
| 62 |
|
| 63 |
https://huggingface.co/bartowski/cognitivecomputations_Dolphin3.0-Mistral-24B-GGUF
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
## Chat Template
|
| 66 |
|
| 67 |
We use ChatML for the chat template.
|
|
|
|
| 62 |
|
| 63 |
https://huggingface.co/bartowski/cognitivecomputations_Dolphin3.0-Mistral-24B-GGUF
|
| 64 |
|
| 65 |
+
## Run Dolphin in Ollama
|
| 66 |
+
|
| 67 |
+
```
|
| 68 |
+
wget https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B/resolve/main/Modelfile
|
| 69 |
+
ollama create Dolphin3-24B
|
| 70 |
+
ollama run Dolphin3-24B
|
| 71 |
+
```
|
| 72 |
+
|
| 73 |
## Chat Template
|
| 74 |
|
| 75 |
We use ChatML for the chat template.
|