Upload README.md with huggingface_hub

README.md

@@ -91,6 +91,15 @@ Best with: target OpenCL, draft CPU, d=3, thread_num=2, power=high.
 ## Usage
 Download via TokForge app: Settings > Spec Decode > Download Acceleration Pack
 
+### Typical TokForge recipe
+
+- target backend: `opencl`
+- draft backend: `cpu`
+- draft threads: `2`
+- `d=3`
+- greedy sampling
+- low precision / low memory
+
 ## Version History
 
 | Version | Samples | KL | Uplift | Date |
@@ -104,3 +113,16 @@ Download via TokForge app: Settings > Spec Decode > Download Acceleration Pack
 **License:** Apache 2.0
 **Source:** KL-distilled from [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) using [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) as teacher
 **Built with:** [TokForge](https://tokforge.ai)
+
+## Limitations and Intended Use
+
+- Best current evidence is strongest on `Qwen3-8B` and `Qwen3-14B`.
+- `Qwen3-4B` was not a strong lane in our preserved results.
+- Device uplift depends heavily on backend routing, prompt length, and thermal state.
+- This is a TokForge-specific runtime bundle, not a standard Transformers checkpoint.
+
+## Community
+
+- Website: [tokforge.ai](https://tokforge.ai)
+- Discord: [Join the Discord](https://discord.gg/Acv3CBtfVm)
+- Collection: [TokForge Mobile Draft Models](https://huggingface.co/collections/darkmaniac7/tokforge-mobile-draft-models-69c36153ea7084ce78329665)