BUG: Fix Codestral v0.1 URI for Pytorch Format (xorbitsai#2590)

qinxuye · Nov 27, 2024 · 0d4cb9c · 0d4cb9c
1 parent 760f31f
commit 0d4cb9c
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/doc/source/models/builtin/llm/codestral-v0.1.rst b/doc/source/models/builtin/llm/codestral-v0.1.rst
@@ -21,8 +21,8 @@ Model Spec 1 (pytorch, 22 Billion)
 - **Model Size (in billions):** 22
 - **Quantizations:** 4-bit, 8-bit, none
 - **Engines**: vLLM, Transformers (vLLM only available for quantization none)
-- **Model ID:** mistralai/Mistral-7B-Instruct-v0.2
-- **Model Hubs**:  `Hugging Face <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2>`__
+- **Model ID:** mistralai/Codestral-22B-v0.1
+- **Model Hubs**:  `Hugging Face <https://huggingface.co/mistralai/Codestral-22B-v0.1>`__
 
 Execute the following command to launch the model, remember to replace ``${quantization}`` with your
 chosen quantization method from the options listed above::

diff --git a/xinference/model/llm/llm_family.json b/xinference/model/llm/llm_family.json
@@ -3411,8 +3411,8 @@
           "8-bit",
           "none"
         ],
-        "model_id": "mistralai/Mistral-7B-Instruct-v0.2",
-        "model_revision": "9552e7b1d9b2d5bbd87a5aa7221817285dbb6366"
+        "model_id": "mistralai/Codestral-22B-v0.1",
+        "model_revision": "8f5fe23af91885222a1563283c87416745a5e212"
       },
       {
         "model_format": "ggufv2",