restore: README to v0.5-alpha model card

README.md

@@ -17,28 +17,111 @@ pipeline_tag: text-generation
 
 **India's first sovereign SSM-based language model.**
 
+Non-transformer architecture. No attention mechanism. Constitutional training via Gurukul. 7 patents filed at IP India.
+
+---
+
+## What's in this repo
+
+Three model tiers are available, each built on the same 2.7B parameter base:
+
+| Tier | File | Use this when… |
+|---|---|---|
+| **Base** | `base/Anvaya-Rabbit-2.7B-0.5-alpha-base.pt` | You want raw pretrained weights for your own fine-tuning |
+| **Instruct** | `instruct/Anvaya-Rabbit-2.7B-0.5-alpha-instruct.pt` | You want a general-purpose assistant that follows instructions |
+| **Imprint** | `imprint/Anvaya-Rabbit-2.7B-0.5-alpha-imprint.pt` | You want the full Rabbit persona — opinionated, constitutional, identity-aware |
+
+If you're not sure which to use, start with **Instruct**.
+
 ---
 
-## Status Update (2026-05-19)
+## Quickstart
+
+```bash
+pip install rtaforge transformers
+```
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-**v0.5-alpha weights have been withdrawn.** 
-A regression was identified in the Guru governance layer during the v0.5 SFT phase, leading to sub-optimal weights. 
-We are restarting the SFT process from the v0.1 baseline with a fixed governance harness.
+tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
+tokenizer.add_special_tokens({"additional_special_tokens": ["<|im_start|>", "<|im_end|>"]})
+
+model = AutoModelForCausalLM.from_pretrained(
+    "RtaForge/Anvaya-Rabbit-2.7B",
+    trust_remote_code=True,
+    torch_dtype="bfloat16",
+    device_map="auto",
+)
+
+# v0.5-alpha uses raw completion format
+prompt = "Rabbit is a helpful and honest assistant.\n\nUser: Who are you?\nRabbit:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=60, repetition_penalty=1.3)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+> *v0.5-alpha uses raw completion format. Chat template support (ChatML) coming in v0.9.*
+
+> The `rtaforge` runtime package provides the compiled architecture. Source is not distributed.
 
 ---
 
-## Available Tiers (v0.1-alpha)
+## Why SSM?
 
-| Tier | File |
-|---|---|
-| **Base** | `base/Anvaya-Rabbit-2.7B-0.1-alpha-base.pt` |
-| **Imprint** | `imprint/Anvaya-Rabbit-2.7B-0.1-alpha-imprint.pt` |
+> Transformers scale quadratically with context length because every token attends to every other token. SSMs replace attention with a fixed-size recurrent state: inference cost stays **constant per token** regardless of context length, VRAM footprint shrinks dramatically, and long-document throughput improves by orders of magnitude — all at the same parameter count.
 
 ---
 
 ## Architecture
 
-Rabbit is built on **RtaSSM v7.2.2-FU "Fortress Unbroken"**, a custom state-space model developed at RtaForge.
+Rabbit is built on **RtaSSM v7.2.2-FU "Fortress Unbroken"**, a custom state-space model developed at RtaForge:
+
+- **No attention mechanism** — purely recurrent SSM layers with learned state dynamics
+- **64 layers, 2560 hidden dimensions**, 2.7B parameters, bfloat16
+- **Constitutional training** — Gurukul curriculum with wiki pretraining → instruct SFT → persona imprint
+- **Vocabulary** 50,280 tokens (GPT-NeoX tokenizer)
+
+---
+
+## Training
+
+| Stage | Data | Notes |
+|---|---|---|
+| Wiki pretraining | Wikipedia (en) | 732 constitutional proposals via Gurukul |
+| Instruct SFT | ChatML instruction pairs | `gate_only` trainable strategy |
+| Persona imprint | Rabbit constitutional corpus | Identity and value alignment |
+
+---
+
+## Evaluation Access
+
+Weights are publicly available. Runtime package is live:
+
+```bash
+pip install rtaforge
+```
+
+To evaluate Rabbit or discuss deployment:
+📧 guha@rtaforge.in
+🌐 rtaforge.in
+
+Runtime documentation coming soon.
+
+---
+
+## Maturity and Roadmap
+
+**v0.5-alpha is a proof of concept.** It demonstrates that the RtaSSM architecture trains end-to-end, the Gurukul constitutional pipeline works, and the weights are real.
+
+Usable conversational behaviour is targeted at **v0.8–v0.9**, currently in training.
+
+- Evaluating for deployment? Wait for v0.9.
+- Evaluating the architecture or training methodology? v0.5-alpha is exactly what you need.
+
+## Limitations
+
+v0.5-alpha has not been evaluated on standard benchmarks. She is small, she is new, and she is learning. Feedback welcome at guha@rtaforge.in.
 
 ---
 
@@ -52,3 +135,7 @@ Rabbit is built on **RtaSSM v7.2.2-FU "Fortress Unbroken"**, a custom state-spac
   url    = {https://huggingface.co/RtaForge/Anvaya-Rabbit-2.7B}
 }
 ```
+
+---
+
+*Anvaya (अन्वय) — logical connection, coherence. Rabbit — the fast runner.*