Rename README and updated

README_4b.md → README.md

@@ -1,6 +1,11 @@
 ---
 license: other
+pipeline_tag: text-generation
+library_name: gguf
+language:
+  - en
 base_model: unsloth/Qwen3-4B-Instruct-2507
+base_model_relation: quantized
 tags:
   - gguf
   - qwen3
@@ -8,7 +13,6 @@ tags:
   - security
   - lora
   - sft
-library_name: gguf
 ---
 
 # Zero Stack - Qwen3-4B (GGUF, Q4_K_M)
@@ -35,6 +39,15 @@ ollama run zerostack-4b
 - Method: LoRA (r=32), 3 epochs, Unsloth
 - Dataset: SFT_GENERALIST (1,226 rows, ChatML)
 
-## License / Use
-For authorized security testing, research, and educational use only. Attribution to RedStack required. Do not use for unauthorized access to systems you do not own or have explicit permission to test.
+## Intended Use
+Authorized security testing, CTF practice, red-team research, and security education. Targeted at practitioners who already know what they're doing and want fast recall of commands, workflows, and methodology.
 
+## Limitations & Risks
+- May hallucinate specific CVE IDs, tool flags, or payload syntax - verify against primary sources before running.
+- No safety guardrails against misuse. Do not use against systems you don't own or have explicit written authorization to test.
+- Small model (4B) - shallower reasoning than the 14B; prefer 14B for multi-step planning.
+- Persona responses are stylistic flavor, not a safety signal.
+- Trained on English data only; non-English performance is not evaluated.
+
+## License / Use
+For authorized security testing, research, and educational use only. Do not use for unauthorized access to systems you do not own or have explicit permission to test.