added Issues to be addressed 🚧

README.md

@@ -43,14 +43,13 @@ This is especially tuned for *game developers* who want believable character dia
 
 | Aspect | Description |
 |--------|--------------|
-| **Base Model** | Qwen3-4B-Instruct (Apache 2.0) |
+| **Base Model** | Qwen/Qwen3-4B-Instruct-2507 (Apache 2.0) |
 | **Method** | Unsloth + TRL LoRA fine-tuning |
 | **LoRA Config** | r=16, alpha=16, 1 epoch, lr=2e-4 |
 | **Dataset** | ~10k RP dialogues: branching quests, adaptive NPCs, synthetic "memory" cues |
-| **Special Token** | `/nothink` for immediate, non-reasoned responses |
 | **Hardware** | Single GPU (T4), 20-minute training |
 | **Quantization** | GGUF Q4_K_M (~2.1GB) for CPU & M1 use |
-| **Eval Summary** | 12% perplexity drop on RP benchmarks; context-aware, non-repetitive NPCs |
+| **Eval Summary** | 12% perplexity drop on RP benchmarks; context-aware, non-repetitive NPCs (still in progress) |
 
 ---
 
@@ -168,6 +167,10 @@ Output:
 
 ---
 
+## 🚧 Found Issues to be addressed
+- Sometimes the model mentions that it's not able to role-play which likely comes in from the quantization and limited fine-tunes.
+- With pre-existing contexts the model can enter an endless repetition loop -> perhaps adjusting my trainings data-sets to capture these systematically will help.
+
 ## 📚 Citation
 
 Schneider, B. (2025). *EmergentRP-Qwen4B* [Fine-tuned model]. Hugging Face.