Update model card: INCEPT.sh v1.0.0, new GitHub URL (0-Time), install.sh, /think toggle

README.md

@@ -11,37 +11,62 @@ tags:
 base_model: Qwen/Qwen3.5-0.8B
 ---
 
-# INCEPT/Sh — Command Inference Model (Q8_0)
+# INCEPT.sh
 
-Fine-tuned **Qwen3.5-0.8B** (GGUF Q8_0, 774MB) for Linux shell command generation. Maps plain English descriptions to accurate Linux commands. Runs entirely offline via [llama.cpp](https://github.com/ggerganov/llama.cpp).
+Offline command inference engine for Linux. Fine-tuned **Qwen3.5-0.8B** (GGUF Q8_0, 774MB) via supervised fine-tuning on 79K Linux command examples. Zero network dependency at runtime.
 
 **Benchmark:** 99/100 on a structured 100-question Linux command evaluation (Ubuntu 22.04, bash, non-root).
 
-## Usage
+## Installation
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/0-Time/INCEPT.sh/main/install.sh | bash
+```
 
-Requires `llama-server` from [llama.cpp](https://github.com/ggerganov/llama.cpp).
+Supports: Debian/Ubuntu, RHEL/Fedora, CentOS, Arch, openSUSE.
+
+## Manual Model Setup
 
 ```bash
 # Download model
 huggingface-cli download 0Time/INCEPT-SH \
-  incept-command-v2-q8_0.gguf --local-dir ./models
+  incept-sh.gguf --local-dir ./models
 
-# Run with INCEPT/Sh CLI
-git clone https://github.com/ProMohanad/INCEPT.sh
+# Clone and install
+git clone https://github.com/0-Time/INCEPT.sh
 cd INCEPT.sh
 pip install -e ".[cli]"
 incept
 ```
 
-Or use directly with llama-server:
+## Usage
 
 ```bash
-llama-server -m models/incept-command-v2-q8_0.gguf --port 8787
+# Interactive CLI
+incept
+
+# One-shot
+incept -c "list all open ports"
+
+# Minimal output (pipe-friendly)
+incept -c "find large files" -m
+
+# With model reasoning
+incept --think
 ```
 
+## CLI Commands
+
+| Command | Description |
+|---|---|
+| `/think on\|off` | Toggle chain-of-thought reasoning |
+| `/context` | Show detected system context |
+| `/help` | List available commands |
+| `/exit` | Exit |
+
 ## Prompt Format
 
-The model uses ChatML format with a system context line:
+ChatML with a system context line:
 
 ```
 <|im_start|>system
@@ -60,23 +85,35 @@ Inference temperature: **0.0** (greedy decoding).
 
 ## Training
 
-| Parameter             | Value                                       |
-|-----------------------|---------------------------------------------|
-| Base model            | Qwen/Qwen3.5-0.8B                           |
-| Training method       | Supervised fine-tuning (LoRA, rank 16)      |
-| Training examples     | 79,264 (SFT) + 11,306 (pipe refinement)    |
-| Learning rate         | 5×10⁻⁵                                     |
-| Quantization          | Q8_0 (774MB)                                |
-| Supported distros     | Ubuntu, Debian, RHEL, Arch, Fedora, CentOS  |
-| Training hardware     | Apple M4 Mac mini, 32GB unified RAM         |
+| Parameter             | Value                                        |
+|-----------------------|----------------------------------------------|
+| Base model            | Qwen/Qwen3.5-0.8B                            |
+| Training method       | Supervised fine-tuning (LoRA, rank 16)       |
+| Training examples     | 79,264 (SFT) + 11,306 (pipe refinement)     |
+| Learning rate         | 5×10⁻⁵                                      |
+| Quantization          | Q8_0 (774MB)                                 |
+| Supported distros     | Ubuntu, Debian, RHEL, Arch, Fedora, CentOS   |
+| Training hardware     | Apple M4 Mac mini, 32GB unified RAM          |
 
 ## Safety
 
-The accompanying [INCEPT/Sh](https://github.com/ProMohanad/INCEPT.sh) engine includes:
-- Prompt injection detection
-- Catastrophic pattern blocking (fork bombs, `rm -rf /`, pipe-to-shell, etc.)
+- Prompt injection detection (exact-phrase matching)
+- Catastrophic pattern blocking (`rm -rf /`, fork bombs, pipe-to-shell, etc.)
 - Risk classification: `SAFE` / `CAUTION` / `DANGEROUS` / `BLOCKED`
+- Zero outbound traffic at runtime
+
+## Requirements
+
+- Linux x86_64 / aarch64
+- Python 3.11+
+- [`llama-server`](https://github.com/ggerganov/llama.cpp) on `PATH`
+- ~1GB RAM at runtime
+
+## Links
+
+- **GitHub:** [0-Time/INCEPT.sh](https://github.com/0-Time/INCEPT.sh)
+- **Release:** [v1.0.0](https://github.com/0-Time/INCEPT.sh/releases/tag/v1.0.0)
 
 ## License
 
-[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+[Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)