Update README.md

README.md

@@ -1,23 +1,55 @@
 ---
-base_model: yanmyoaung/deepseek-cybersecurity-model-v1.0
+base_model: unsloth/DeepSeek-R1-Distill-Llama-8B
 tags:
-- text-generation-inference
+- text-generation
 - transformers
 - unsloth
+- deepseek
 - llama
 - trl
-- sft
 license: apache-2.0
 language:
 - en
 ---
 
-# Uploaded  model
+# DeepSeek Cybersecurity Model v1.1
 
-- **Developed by:** yanmyoaung04
-- **License:** apache-2.0
-- **Finetuned from model :** yanmyoaung/deepseek-cybersecurity-model-v1.0
+This is a fine-tuned version of **Unsloth’s DeepSeek-R1-Distill-Llama-8B** model, adapted for cybersecurity-focused text generation tasks.
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+### Overview
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+- **Base model:** [`unsloth/DeepSeek-R1-Distill-Llama-8B`](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B)  
+- **Developer:** [yanmyoaung](https://huggingface.co/yanmyoaung)  
+- **Fine-tuned with:** [Unsloth](https://github.com/unslothai/unsloth) + Hugging Face [TRL](https://github.com/huggingface/transformers/tree/main/examples/research_projects/trl)  
+- **Merged Weights:** LoRA adapter merged into base model (16-bit)  
+- **License:** Apache 2.0
+
+### Model Purpose
+
+This model is optimized for generating and understanding cybersecurity-related content, such as:
+
+- Threat intelligence summaries  
+- Vulnerability analysis  
+- Incident response suggestions  
+- Cybersecurity Q&A and explanation generation
+
+### Inference Example
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("yanmyoaung04/deepseek-cybersecurity-model-v1.1")
+tokenizer = AutoTokenizer.from_pretrained("yanmyoaung04/deepseek-cybersecurity-model-v1.1")
+
+prompt = "Explain what a buffer overflow vulnerability is."
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=150)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+```
+
+### License
+
+Apache 2.0 — free for academic and commercial use.
+
+---