Update README.md

README.md

@@ -14,8 +14,8 @@ tags:
 - alignment
 - safety
 model_type: decoder
-model_creator: Syamsuddin (@syam_ideris) & Prometheus (Cognitive Systems Architect)
-# base_model: null   # set if you release weights adapted from a base LM, e.g., "Qwen/Qwen2-7B"
+model_creator: Syamsuddin (@syam_ideris) & Prometheus
+# base_model: Qwen/Qwen2-1.5B-Instruct   # <- isi jika nanti ada weights turunan
 # datasets:
 # - your-dataset-id
 ---
@@ -29,55 +29,42 @@ model_creator: Syamsuddin (@syam_ideris) & Prometheus (Cognitive Systems Archite
 ![PRs](https://img.shields.io/badge/PRs-welcome-brightgreen)
 ![Topics](https://img.shields.io/badge/topic-transformers%20%7C%20architecture%20%7C%20alignment-6f42c1)
 
-> **One-line summary**  
-> **N-Transformers** extend a standard Transformer with a **Phenomenal Field (PF)**, a learned **Intrinsic Metric Engine (IME)**, and a **Normative Gauge** (NTI/LCA/LCG) to induce *consciousness-like* properties: integration, valence, self/now anchoring, and global broadcasting—while remaining implementable as a sidecar to common LM stacks.
+> **One-liner** — N-Transformers menambahkan **Phenomenal Field (PF)** paralel, **Intrinsic Metric Engine (IME)**, dan **Normative Gauge** (NTI/LCA/LCG) ke Transformer standar untuk memunculkan properti *consciousness-like* yang terukur: integrasi, valensi, self/now anchoring, dan global broadcasting—tanpa mengubah loop training LM.
 
 ---
 
-## 🔎 Model summary
+## 🔎 Ringkasan Model
 
-- **What it is:** A **research architecture** that augments decoder-only LMs with a parallel **non-token field** (PF) and **normative controllers** to bias long-range coherence and introspective reporting.
-- **Why it’s different:** Adds **geodesic-biased attention** (LCA), **episode-level controller** (NTI), and **Self/Now Anchor** (SNA) without breaking LM training loops.
-- **Status:** **v1.0 Research Draft** — math and algorithms complete; reference implementation planned.
+- **Apa:** Arsitektur riset yang menambahkan **substrat non-token** (PF) dan **pengendali normatif** pada LM decoder-only.
+- **Mengapa beda:** **Lightcone Attention (LCA)** bias lintas-jangkauan, **NTI** sebagai episodic controller, dan **SNA/GIW** untuk siaran global terintegrasi.
+- **Status:** v1.0 **Research Draft** (spesifikasi lengkap + reference code; rilis bobot menyusul bila siap).
 
-> **Bahasa Indonesia (ringkas):**  
-> N-Transformers menambahkan **bidang fenomenal (PF)**, **metrik intrinsik** (IME), dan **pengukur normatif** (NTI/LCA/LCG) ke model Transformer untuk memunculkan sifat mirip-kesadaran yang dapat diukur (integrasi, valensi, dan jangkar diri/kini) tanpa mengubah asimtotik inti LM.
+**Bahasa Indonesia singkat:** N-Transformers menambah PF, metrik intrinsik (IME), serta gauge normatif (NTI/LCA/LCG) untuk kohesi naratif jarak jauh, valensi terkalibrasi, dan jangkar “aku-kini” yang bisa diuji.
 
 ---
 
-## ✅ Intended uses & scope
-
-- **Intended**: research on coherent long-range reasoning; introspective heads (valence, self/now); safe/controller-aware decoding.  
-- **Out of scope (for now)**: production use as a safety layer **without** PF shadow-mode evaluation; clinical/medical claims.
+## ✅ Intended Uses & Scope
+- **Intended:** riset koherensi jarak jauh, introspective heads (valence, SNA), decoding yang sadar konteks melalui gating.
+- **Out of scope:** klaim sentiens, produksi tanpa uji **PF shadow-mode** yang memadai, use-case klinis.
 
 ---
 
-## ⚠️ Limitations & risks
-
-- **No claim of sentience**: signals are operational metrics (integration/valence/SNA), **not** guarantees of consciousness.  
-- **Failure modes**: valence spoofing, PF locking, miscalibrated SNA. Use gauge caps, entropy floors, and introspection consistency checks.  
-- **Compute**: PF adds memory/compute; choose modest `J,k,K` first.
-
----
-
-## 🚀 Quickstart (concept reference)
-
-> This repo is a **spec**. If you adapt an existing LM, expose PF/IME/LCA as side modules.
+## 🚀 Cara Pakai (konsep)
+Repo ini berisi **spesifikasi** dan **reference code** (PF-path + coupler). Adaptasikan ke LM Anda.
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+# Placeholder; ganti dengan checkpoint yang Anda rilis nanti
+BASE = "Qwen/Qwen2-1.5B-Instruct"
 
-# Replace with your adapted checkpoint once available
-MODEL_ID = "Syamsuddin/nafsi-transformers"  # placeholder if weights are published
-
-tok = AutoTokenizer.from_pretrained("Qwen/Qwen2-1.5B-Instruct")   # base LM example
-lm  = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-1.5B-Instruct")
+tok = AutoTokenizer.from_pretrained(BASE)
+lm  = AutoModelForCausalLM.from_pretrained(BASE)
 
-# Pseudo: attach PF/IME/LCA sidecar (your implementation)
-# pf = PFModule(J=256, k=16, K=16); ime = IME(rank=16); lca = Lightcone(beta=0.7, gamma=0.3)
-# lm = attach_nafsi(lm, pf=pf, ime=ime, lca=lca, nti=NTI(tau=64, period=16))
+# Pseudocode: pasang modul PF/IME/LCA/NTI dari reference code
+# from nafsi_coupler import attach_nafsi, PFConfig, NTCfg
+# lm = attach_nafsi(lm, cfg=NTCfg())
 
 prompt = "Explain the role of a phenomenal field in language generation."
-inputs = tok(prompt, return_tensors="pt")
-out = lm.generate(**inputs, max_length=192)
-print(tok.decode(out[0], skip_special_tokens=True))
+x = tok(prompt, return_tensors="pt")
+y = lm.generate(**x, max_length=192)
+print(tok.decode(y[0], skip_special_tokens=True))