chore: bump phi-3 version

umbertogriffo · Jul 8, 2024 · 14b6bc6 · 14b6bc6
1 parent 9457610
commit 14b6bc6
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -145,7 +145,7 @@ format.
 | `dolphin` Dolphin 2.6 Mistral DPO Laser       | ✅         | 7B         | [link](https://huggingface.co/TheBloke/dolphin-2.6-mistral-7B-dpo-laser-GGUF)                                                                                        |
 | `zephyr` Zephyr Beta                          | ✅         | 7B         | [link](https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF)                                                                                                          |
 | `mistral` Mistral OpenOrca                    | ✅         | 7B         | [link](https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF)                                                                                                     |
-| `phi-3` Phi-3 Mini 4K Instruct                | ✅         | 3.8B       | [link](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf)                                                                                                 |
+| `phi-3` Phi-3 Mini 4K Instruct                | ✅         | 3.8B       | [link](https://huggingface.co/bartowski/Phi-3.1-mini-4k-instruct-GGUF)                                                                                               |
 | `stablelm-zephyr` StableLM Zephyr OpenOrca    | ✅         | 3B         | [link](https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF)                                                                                                      |
 
 ## Supported Response Synthesis strategies

diff --git a/chatbot/bot/model/settings/phi_3.py b/chatbot/bot/model/settings/phi_3.py
@@ -3,8 +3,8 @@
 
 
 class PhiThreeSettings(Model):
-    url = "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf"
-    file_name = "Phi-3-mini-4k-instruct-q4.gguf"
+    url = "https://huggingface.co/bartowski/Phi-3.1-mini-4k-instruct-GGUF/resolve/main/Phi-3.1-mini-4k-instruct-Q5_K_M.gguf"
+    file_name = "Phi-3.1-mini-4k-instruct-Q5_K_M.gguf"
     clients = [LlmClientType.LAMA_CPP]
     config = {
         "n_ctx": 4096,  # The max sequence length to use - note that longer sequence lengths require much more resources