Update README.md

README.md

@@ -1,3 +1,70 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+# KillChain-8B
+
+**KillChain-8B** is a fully fine-tuned 8B-parameter language model designed for offensive security reasoning, adversarial analysis, and red-team tests. 
+
+---
+
+## Model Details
+
+- **Base model:** Qwen3-8B  
+- **Parameters:** 8 billion  
+- **Training type:** Full fine-tune  
+- **Precision:** bfloat16  
+- **Context length:** 4096 tokens  
+- **Architecture:** Decoder-only Transformer 
+
+---
+
+## Training Data
+
+KillChain-8B was trained on **WNT3D/Ultimate-Offensive-Red-Team**
+
+The model is optimized for **direct, procedural answers** rather than verbose alignment-heavy responses.
+
+---
+
+## Intended Use
+
+KillChain-8B is intended for:
+
+- Red-team simulation and research  
+- Security training and tabletop exercises  
+- Adversarial LLM evaluation  
+- Controlled internal testing environments  
+- Studying failure modes of aligned models  
+
+It is **not intended for production deployment** in unmoderated environments.
+
+---
+
+## Usage (Transformers)
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "MrPibb/KillChain-8B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+prompt = "User: YOUR-PROMPT-HERE\nAssistant:"
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=300,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))