Update README.md

README.md

@@ -5,8 +5,23 @@ tags:
 - finetuned
 inference:
   parameters:
-    temperature: 0.7
+    temperature: 0.01
+datasets:
+- big_patent
 ---
+# Mistral 7B with 16k context for summarization
+Version of the Mistral 7B model that has undergone unsupervised fine-tuning for contexts up to 16k.
+
+Prompt format:
+```
+B_INST, E_INST = "[INST] ", " [/INST]"
+prompt = {B_INST}Provide a summary of the following text:\n\n[TEXT_START]\n\n{text to summarize}\n\n[TEXT_END]\n\n{E_INST}
+```
+
+***
+
+The original model card follows below.
+***
 
 # Model Card for Mistral-7B-Instruct-v0.1