mistralai
/

Pixtral-Large-Instruct-2411

Model card Files Files and versions

patrickvonplaten commited on Nov 15, 2024

Commit

17cd500

·

verified ·

1 Parent(s): 3a0e7b6

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -145,7 +145,8 @@ For more details about this model please refer to our release [blog post](https:
 - **Vision:** A 1B parameter Vision Encoder achieving SOTA vision capabilities.
 -->
-### System Prompt
 We appreciate the feedback received from our community regarding our system prompt handling.
 In response, we have implemented stronger support for system prompts.
 To achieve optimal results, we recommend always including a system prompt that clearly outlines the bot's purpose, even if it is minimal.
@@ -294,7 +295,7 @@ You can also use Pixtral-Large-Instruct-2411 in a server/client setting.
 1. Spin up a server:
 ```
-vllm serve mistralai/Pixtral-Large-Instruct-2411 --tokenizer_mode mistral --limit_mm_per_prompt 'image=4' --tensor_parallel_size 8
 ```
 2. And ping the client:

 - **Vision:** A 1B parameter Vision Encoder achieving SOTA vision capabilities.
 -->
+### System Prompt Handling
 We appreciate the feedback received from our community regarding our system prompt handling.
 In response, we have implemented stronger support for system prompts.
 To achieve optimal results, we recommend always including a system prompt that clearly outlines the bot's purpose, even if it is minimal.
 1. Spin up a server:
 ```
+vllm serve mistralai/Pixtral-Large-Instruct-2411 --tokenizer_mode mistral --limit_mm_per_prompt 'image=10' --tensor-parallel-size 8 --tool-call-parser mistral --enable-auto-tool-choice
 ```
 2. And ping the client: