Update README.md

README.md

@@ -16,6 +16,15 @@ language:
 - **License:** apache-2.0
 - **Finetuned from model :** unsloth/gpt-oss-20b-unsloth-bnb-4bit
 
+ACI_Cyber_Base_GPT_OSS_20B is an LLM derivied from openai/gpt-oss:20b, continued pretrained with security related corpus including computer security QA, CVE descriptions, MITRE ATTCK framework descriptions, Incident Response playbooks, and penetration testing knowledge QA.
+
+Multi-judge experiment demonstrates that this model consistently outperforms openai/gpt-oss:20b in SOC investigation planning:
+
+![vote_judges](https://cdn-uploads.huggingface.co/production/uploads/6665d197d8e1e34bc6b5c747/HiX3P7xVYRRs0qU9wQNV7.png)
+![vote_majority](https://cdn-uploads.huggingface.co/production/uploads/6665d197d8e1e34bc6b5c747/hM7NSoJ5Ujpq_aU4Sr-tm.png)
+
+Detailed experiment is documented [here](https://github.com/Automatic-Case-Investigator/ACI_Training_Experiment)
+
 This gpt_oss model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)