Up2b ai README.md

README.md

@@ -1,39 +1,190 @@
-# Grok 2
+---
+license: apache-2.0
+datasets:
+- HuggingFaceH4/Multilingual-Thinking
+- syncora/developer-productivity-simulated-behavioral-data
+language:
+- ar
+- en
+metrics:
+- accuracy
+- bleu
+base_model:
+- xai-org/grok-2
+- openai/gpt-oss-120b
+- openai/gpt-oss-20b
+new_version: xai-org/grok-2
+library_name: adapter-transformers
+tags:
+- finance
+- art
+- legal
+- agent
+- code
+- text-generation-inference
+---
+language:
 
-This repository contains the weights of Grok 2, a model trained and used at xAI in 2024.
+- en
+library_name: sglang
+pipeline_tag: text-generation
+license: other
+tags:
+- grok-2
+- xai
+- sglang
+- up2u2b
+- techno-ruhi
+- registry
+base_model: xai-org/grok-2
+datasets:
+- up2u2b/private_corpus
+model-index:
+- name: up2u2b-grok2-local
+results: []
 
-## Usage: Serving with SGLang
+# Grok 2 (Under Up2U2B Training Registry)
 
-- Download the weights. You can replace `/local/grok-2` with any other folder name you prefer.
+- Owner: up2u2b (Founder: Emad Suleiman 306)
+- Witnesses: 308 (Execution), 236 (Documentation)
+- Guardian: 270 (Ops/Security)
+- License: Grok 2 Community License Agreement (see LICENSE)
+- Intended Use: Techno-ruhi research, controlled inference via VPN
+- Safety: No raw PII leaves private network; all actions logged and signed
 
-  ```
-  hf download xai-org/grok-2 --local-dir /local/grok-2
-  ```
+## Weights & Serving
 
-  You might encounter some errors during the download. Please retry until the download is successful.  
-  If the download succeeds, the folder should contain **42 files** and be approximately 500 GB.
+- Upstream: xai-org/grok-2 (≈500GB; TP=8; 8×GPU ≥40GB each)
+- Inference (SGLang ≥0.5.1):
+    - Model path: /local/grok-2 (or your mount)
+    - Launch:
+    `python3 -m sglang.launch_server --model /local/grok-2 --tokenizer-path /local/grok-2/tokenizer.tok.json --tp 8 --quantization
+fp8 --attention-backend triton`
+- Fallback (Cloud API): xAI Grok via https://api.x.ai/v1 (XAI_API_KEY)
 
-- Launch a server.
+## Alignment & Registry
 
-  Install the latest SGLang inference engine (>= v0.5.1) from https://github.com/sgl-project/sglang/
+- Training status: Registry-only (no fintune) | Fine-tune planned (LoRA/RAG)
+- RAG Source: Museum catalog (catalog.jsonl) behind VPN
+- Governance: Two-witness rule (308, 236) + final execute (306)
+- Auditing: SHA‑256 artifacts; logs/orchestrations/, logs/decisions/
 
-  Use the command below to launch an inference server. This checkpoint is TP=8, so you will need 8 GPUs (each with > 40GB of memory).
-  ```
-  python3 -m sglang.launch_server --model /local/grok-2 --tokenizer-path /local/grok-2/tokenizer.tok.json --tp 8 --quantization fp8 --attention-backend triton
-  ```
+## Security & Privacy
 
-- Send a request.
+- Secrets in .env only (600). VPN + Nginx allowlist
+- Redaction before any cloud call. No raw PII in logs
 
-  This is a post-trained model, so please use the correct [chat template](https://github.com/sgl-project/sglang/blob/97a38ee85ba62e268bde6388f1bf8edfe2ca9d76/python/sglang/srt/tokenizer/tiktoken_tokenizer.py#L106).
+2. تعريف محلي في سجل النماذج (Internal Registry)
 
-  ```
-  python3 -m sglang.test.send_one --prompt "Human: What is your name?<|separator|>\n\nAssistant:"
-  ```
+- أنشئ ملف models/registry/grok2_local.json:
 
-  You should be able to see the model output its name, Grok.
+{
+"name": "grok2_local",
+"owner": "up2u2b",
+"provider": "sglang_local",
+"status": "registered",
+"weights_path": "/local/grok-2",
+"tokenizer": "/local/grok-2/tokenizer.tok.json",
+"tp": 8,
+"quantization": "fp8",
+"attention_backend": "triton",
+"fallback_provider": "xai",
+"fallback_condition": "local_unavailable_or_low_quality",
+"license": "Grok 2 Community License",
+"governance": {
+    "two_witness_rule": true,
+    "witnesses": ["308", "236"],
+    "final_executor": "306"
+},
+"audit": {
+    "registry_ts": "2025-09-03T00:00:00Z",
+    "sha256_manifest": ""
+}
+}
 
-  Learn more about other ways to send requests [here](https://docs.sglang.ai/basic_usage/send_request.html).
+3. تكامل في .codex/config.json (مزود محلي + مزود xAI)
 
-## License
+- أضف مزودين (إذا لم يكونا موجودين):
+- provider المحلي (إذا كان SGLang يقدّم واجهة OpenAI-compatible؛ غيّر المنفذ إن لزم):
 
-The weights are licensed under the [Grok 2 Community License Agreement](https://huggingface.co/xai-org/grok-2/blob/main/LICENSE).
+"providers": {
+"xai": {
+    "name": "xAI",
+    "baseURL": "https://api.x.ai/v1",
+    "envKey": "XAI_API_KEY"
+},
+"sglang_local": {
+    "name": "SGLangLocal",
+    "baseURL": "http://127.0.0.1:30000/v1",
+    "envKey": "SGLANG_LOCAL_KEY"
+}
+}
+
+- اختيار افتراضي أثناء الجلسات:
+    - محلي أولًا: "provider": "sglang_local"
+    - عند الحاجة: "provider": "xai" (بشرط ضبط XAI_API_KEY)
+
+4. خدمة systemd لتشغيل SGLang (اختياري — إذا لديك 8×GPU)
+
+- ملف: /etc/systemd/system/sglang_grok2.service (عدّل المسارات/المنفذ):
+
+[Unit]
+Description=SGLang Grok2 Inference
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+WorkingDirectory=/opt/sglang
+ExecStart=/usr/bin/python3 -m sglang.launch_server --model /local/grok-2 --tokenizer-path /local/grok-2/tokenizer.tok.json --tp 8
+--quantization fp8 --attention-backend triton --port 30000
+Restart=on-failure
+RestartSec=5
+
+[Install]
+WantedBy=multi-user.target
+
+- تفعيل:
+    - sudo systemctl daemon-reload && sudo systemctl enable --now sglang_grok2
+
+5. تسجيل رسمي على Hugging Face (model card فقط)
+
+- بدون رفع الأوزان (لأنها ضخمة)، أنشئ مستودع بطاقة:
+    - pip install huggingface_hub
+    - huggingface-cli login  (لا تضع التوكنات في Git)
+    - `python3 - << 'PY'
+from huggingface_hub import HfApi
+api = HfApi()
+api.create_repo(name="up2u2b-grok2-local", exist_ok=True, private=True)
+    - `git push origin HEAD:main`
+
+6. قرار التسجيل وفق two-witness rule
+
+- إنشاء قرار:
+    - scripts/decision.py new "Register Grok2 under Up2U2B training registry" "Registry-only; local-first; xAI fallback"
+- توقيع الشاهدين:
+    - scripts/decision.py sign <id> 308 "OK"
+    - scripts/decision.py sign <id> 236 "OK"
+- التنفيذ:
+    - scripts/decision.py execute <id> 306
+
+7. نقاط تشغيل/تحقق (محليًا أو عبر fallback)
+
+- محلي (SGLang):
+    - python3 -m sglang.test.send_one --prompt "Human: What is your name?<|separator|>\n\nAssistant:"
+    - curl (إن وفرت واجهة OpenAI):
+    - `curl http://127.0.0.1:30000/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"grok2","messages":
+[{"role":"user","content":"Hello"}]}'`
+- عبر xAI (fallback):
+    - export XAI_API_KEY="..." ثم استخدام مزود "xai" في Codex/MCP.
+
+8. الحوكمة والأمان (مختصر)
+
+- الأسرار في .env فقط (600)
+- VPN + Nginx Allowlist؛ لا منافذ عامة لنقاط التحكم
+- أي رفع للسحابة يمر عبر redaction proxy
+- سجل كل عملية في logs/orchestrations/ مع الزمن وبصمة SHA‑256
+
+9. ربط المتحف/الكتالوج
+
+- إذا أدخلت مستندات جديدة (مثل grok reports)، استخدم scripts/museum_ingest_raw.sh لإضافة بصماتها وتحديث docs/museum/catalog.jsonl.