Update README.md

README.md

@@ -12,7 +12,7 @@ lm_studio:
   use_case: coding
   release_date: 29-05-2024
   model_creator: mistralai
-  prompt_template: none 
+  prompt_template: Mistral Instruct 
   system_prompt: none
   base_model: mistral
   original_repo: mistralai/Codestral-22B-v0.1
@@ -26,6 +26,33 @@ base_model: mistralai/Codestral-22B-v0.1
 **Original model**: [Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1)<br>
 **GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3024](https://github.com/ggerganov/llama.cpp/releases/tag/b3024)<br>
 
+## Model Summary:
+
+Codestral is a brand new coding model released by the Mistral team. This 22B model is the first of its size and the first ever specialized model released by this team.<br>
+Supporting both instruction prompting and popular Fill in the Middle (FIM) tokens for predictions, this model should be all around great for all your coding tasks.
+
+## Prompt template:
+
+Choose the `Mistral Instruct` preset in your LM Studio.
+
+Under the hood, the model will see a prompt that's formatted like so:
+
+```
+<s>[INST]  {prompt} [/INST]</s>
+```
+
+This model also supports the following FIM tokens:
+
+`<fim_prefix>`, `<fim_suffix>`, `<fim_middle>`
+
+## Technical Details
+
+Codestral 22B 0.1 is trained on a dataset of 80+ programming languages including of course Python, Java, C++, Javascript, and Bash.
+
+It supports both instruction querying as well as Fill in the Middle querying.
+
+More details and benchmark information can be found on their blogpost here: https://mistral.ai/news/codestral/
+
 ## Special thanks
 
 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/)