Update README.md

README.md

@@ -1,3 +1,88 @@
 ---
 license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- roleplay
+- creative-writing
+- local-llm
+- cpu-inference
+library_name: transformers
 ---
+
+# Roleshade 230M
+
+**Status: 🚧 Weights pending release — expected in 2–3 weeks.**
+
+Roleshade 230M is a 230-million-parameter model built by [Lightshade](https://new.lightshade.cloud) for **roleplay and creative writing**. It is designed to run well on hardware people actually own — phones, laptops, and CPU-only machines — without giving up long-context conversations.
+
+This repository is a placeholder. Model files, quantizations, and usage examples will be published here on release.
+
+---
+
+## Highlights
+
+- **Purpose-built for character work.** Trained for persona consistency, scene memory, and prose that resists the repetition collapse common at this parameter count.
+- **Fast prefill on CPUs and phones.** Roleshade 230M uses a custom architecture that addresses the prefill bottleneck that makes long-context local models painful on non-GPU hardware. Loading a long chat history doesn't mean waiting on a spinner.
+- **Long context, anywhere.** Deep, persistent roleplay sessions on a laptop, desktop, or phone.
+- **Extremely lightweight.** At 230M parameters, this is Lightshade's smallest Roleshade variant — built for devices where even 1B-class models are too heavy.
+- **Local by default.** Runs entirely on your own machine. Nothing leaves the device.
+
+---
+
+## Intended Use
+
+**Primary:** Interactive roleplay, character simulation, collaborative fiction, and creative writing assistance on constrained hardware.
+
+**Out of scope:** Factual question answering, coding assistance, math, retrieval-grounded work, safety-critical applications, or any use where the model's output is treated as authoritative. Roleshade 230M is a creative model and will confidently produce fiction.
+
+---
+
+## Usage
+
+Code samples will be added when weights are published.
+
+```python
+# Available on release
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "lightshade/roleshade-230m"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+```
+
+Roleshade 230M will also be available directly on **LSAI** at launch — one click, no setup required.
+
+Recommended sampler settings and prompt/character-card formatting will be documented here at release.
+
+---
+
+## Limitations
+
+- At 230M parameters, world knowledge is very limited. Expect confident hallucination on factual topics, more so than larger Roleshade variants.
+- Optimized for creative output; general instruction-following outside of roleplay contexts should not be expected to be strong.
+- Long-session coherence is solid for the size class but not unlimited, and simpler than larger models on complex, multi-thread scenes.
+- English-first. Other languages are untested.
+- Best suited for lightweight, casual roleplay rather than nuanced or highly demanding creative writing tasks — for those, consider a larger Roleshade variant.
+
+## Responsible Use
+
+This model is intended for adult creative fiction and roleplay. Users are responsible for how they deploy it and for complying with applicable law and the terms of any platform they run it on. Outputs are fiction and should not be relied on as advice of any kind.
+
+---
+
+## License
+
+Apache 2.0 (subject to confirmation at release).
+
+## Citation
+
+```bibtex
+@misc{roleshade230m,
+  title  = {Roleshade 230M},
+  author = {Lightshade},
+  year   = {2026},
+  url    = {https://huggingface.co/LightshadeML/Roleshade-230M}
+}
+```