Update README.md

README.md

@@ -10,12 +10,10 @@ library_name: transformers
 
 ## Model Description
 
-Radiantloom Email Assist 7B is an email-assistant large language model fine-tuned from [Zephyr-7B-Beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), over a custom-curated dataset of 1,000 email-assistant summarization tasks prepared by AI Geek Labs. It is licensed for commercial use.
+Radiantloom Email Assist 7B is an email-assistant large language model fine-tuned from [Zephyr-7B-Beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), over a custom-curated dataset of 1,000 email-assistant summarization tasks prepared by AI Geek Labs. The context lenght for the model is 4096 and it is licensed for commercial use.
 
 ## Intended Uses & Limitations
-The model is fine-tuned specifically for summarizing short personal and business emails, converting them into voice memos, or chat messages.
-
-The context length for fine-tuning was set at 512 tokens. Therefore, we recommend keeping the email text under 400 tokens to allow room for both the instructions and the output text.
+The model is fine-tuned specifically for summarizing personal and business emails, converting them into voice memos, or chat messages.
 
 radiantloom-email-assist-7b is not a state-of-the-art generative language model and is not designed to perform competitively on general tasks with more modern model architectures or models subject to larger pretraining corpuses.