Update README.md

README.md

@@ -5,9 +5,10 @@ datasets:
 pipeline_tag: text-generation
 ---
 
-Note: We offer a temporary HF inference endpoint for community use.
-Initially, it may take a few minutes to start, but subsequent use will match the usual speed of HF's 7B model text inference endpoint.
-This endpoint is intended for initial testing, not for production purposes:
+Note: Our temporary HF inference endpoint is available for community testing.
+It may initially take a few minutes to activate, but will eventually operate at the standard speed of HF's 7B model text inference endpoint.
+The speed of inference depends on HF endpoint performance and is unrelated to Snorkel offerings.
+This endpoint is designed for initial trials, not for ongoing production use. Have fun!
 
 ```
 import requests
@@ -44,7 +45,9 @@ We utilize ONLY the prompts from [UltraFeedback](https://huggingface.co/datasets
 This overview provides a high-level summary of our approach. 
 We plan to release more detailed results and findings in the coming weeks on the [Snorkel blog.](https://snorkel.ai/blog/)
 
-The prompt format follows Mistral model: `[INST] {prompt} [/INST]`
+The prompt format follows the Mistral model:
+
+```[INST] {prompt} [/INST]```
 
 ### Training recipe:
 - The provided data is formatted to be compatible with the Hugging Face's [Zephyr recipe](https://github.com/huggingface/alignment-handbook/tree/main/recipes/zephyr-7b-beta).