Update README.md

README.md

@@ -1,18 +1,18 @@
 ---
-language: 
+language:
 - en
-- zh 
-- ja 
-- ko 
-- fr 
-- es 
-- pt 
-- de 
-- it 
-- ru 
-- ar 
-- vi 
-- th 
+- zh
+- ja
+- ko
+- fr
+- es
+- pt
+- de
+- it
+- ru
+- ar
+- vi
+- th
 tags:
 - code
 - coding
@@ -25,50 +25,56 @@ license: gpl-3.0
 
 # JiRack Coder 7B INT8
 
-A fast and efficient coding assistant with a clean built-in web UI, powered by Qwen2.5-Coder-7B-Instruct base and optimized using Microsoft ONNX Runtime.
+A fast and efficient coding assistant with a clean built-in web UI, powered by **Qwen2.5-Coder-7B-Instruct** and optimized using Microsoft ONNX Runtime.
 
-- JiRack is cloud model and save money on cloud and can be used as expert model in RAG on cloud with ONNX JiRack java server as alternative.
+- JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative.
 
 ## Quick Start
-Watch the JiRack Coder 7B in action:
-**DEMO**: [JiRack Coder 7B Web UI](https://youtu.be/I8AAITUiI64)
 
+Watch JiRack Coder 7B in action:
+
+**DEMO**: [JiRack Coder 7B Web UI](https://youtu.be/I8AAITUiI64)
 
 ### Run with Docker
 
----
---Default CPU--
+**Default CPU**
 
-- docker run -d \
+```bash
+docker run -d \
   --name jirack_coder_7b \
   -p 7869:7869 \
   --restart unless-stopped \
   cmsmanhattan/jirack_coder_7b_int8_qwenbase:latest
+```
 
---Multi CPU--
+**Multi CPU**
 
-- docker run -d \
+```bash
+docker run -d \
   --name jirack_coder_7b \
   -p 7869:7869 \
   --restart unless-stopped \
   --memory=20g \
   --cpus=12 \
   cmsmanhattan/jirack_coder_7b_int8_qwenbase:latest
+```
 
----GPU--
-
-- docker run -d \
-   --name jirack_coder_7b \
-   -p 7869:7869 \
-   --gpus all \
-   --restart unless-stopped \
-   cmsmanhattan/jirack_coder_7b_int8:1.0.2
+**GPU**
 
----
-services:
+```bash
+docker run -d \
+  --name jirack_coder_7b \
+  -p 7869:7869 \
+  --gpus all \
+  --restart unless-stopped \
+  cmsmanhattan/jirack_coder_7b_int8:1.0.2
+```
 
+### Docker Compose Example
 
-    
+```yaml
+services:
+  jirack:
     image: cmsmanhattan/jirack_coder_7b_int8:1.0.2
     container_name: jirack_onnx_service
     ports:
@@ -86,15 +92,16 @@ services:
     deploy:
       resources:
         limits:
-          memory: 16g 
+          memory: 16g
+```
 
 ## Access the UI
 
 Once the container is running, open your browser and navigate to:
 
-**`http://localhost:7869`**
+`http://localhost:7869`
 
-This opens the **JiRack Coder UI** — a clean web interface designed for coding.
+This opens the JiRack Coder UI — a clean web interface designed for coding.
 
 ## Changing the Port
 
@@ -102,56 +109,56 @@ The listening port can be easily modified directly from the **Settings** panel w
 
 ## Licensing
 
-- The **JiRack Coder 7B model** is released under the **GNU General Public License v3.0 (GPL-3.0)**.
-- All **JiRack UI clients** are provided under a commercial license.
+- The JiRack Coder 7B model is released under the GNU General Public License v3.0 (GPL-3.0).
+- All JiRack UI clients are provided under a commercial license.
 - However, the UI clients can be used for free when running together with the official JiRack Docker containers, as long as they are not redistributed separately.
 
-**JiRack Coder 32B** is available exclusively under a commercial enterprise license.
+JiRack Coder 32B is available exclusively under a commercial enterprise license.
 
-- JiRack Coder 32B https://huggingface.co/CMSManhattan/JiRackCoderReasoing_32b
+## Other JiRack Coder Models
 
-- JiRack Coder 14B https://huggingface.co/CMSManhattan/JiRackCoderReasoing_14b
+- JiRack Coder 32B
+- JiRack Coder 14B
+- JiRack Coder 8B
 
-- JiRack Coder 8B https://huggingface.co/CMSManhattan/JiRackCoderReasoing_8b
+For commercial licensing, cluster deployment, or enterprise use, please contact us.
 
-For commercial licensing, cluster deployment, or enterprise use of the JiRack Coder 32B and JiRack Coder 14B , please contact us.
-- JiRack MS Windows 11  Desktop chat client with  ollama API setup : https://huggingface.co/kgrabko/JiRackTernary_1b/resolve/main/jirack-chat.zip
-- Live email chat with model via support@cmsmanhattan.com
+- **JiRack MS Windows 11 Desktop Client (with Ollama API):**  
+  https://huggingface.co/kgrabko/JiRackTernary_1b/resolve/main/jirack-chat.zip
 
+- **Live email chat with the model:** support@cmsmanhattan.com
 
 ## Hardware Recommendations for AMD Systems
 
-### Recommended Hardware for JiRack Coder 7B INT8 . It is one dcoker container
+### Recommended Hardware for JiRack Coder 7B INT8 (single Docker container)
 
-| Use Case              | CPU                              | GPU (ROCm)                        | VRAM / RAM     | Expected Speed      | Recommendation     |
-|-----------------------|----------------------------------|-----------------------------------|----------------|---------------------|--------------------|
-| **Recommended**       | Ryzen 7 7700 / 9700X             | RX 7900 XTX / 7900 XT             | 24GB VRAM      | 50-75 tokens/s      | Best choice        |
-| **High Performance**  | Ryzen 9 7950X / 9950X            | RX 7900 XTX                       | 24GB+ VRAM     | 65-90 tokens/s      | Excellent          |
-| **Enterprise**        | EPYC 7003/9004 series            | MI300X or 2x RX 7900 XTX          | 48GB+ VRAM     | 90-140 tokens/s     | For 32B model      |
-| **Budget Option**     | Ryzen 5 7600 / 9600X             | RX 7800 XT (16GB)                 | 16GB VRAM      | 35-50 tokens/s      | Acceptable         |
+| Use Case         | CPU                      | GPU (ROCm)                | VRAM / RAM | Expected Speed   | Recommendation |
+|------------------|--------------------------|---------------------------|------------|------------------|----------------|
+| Recommended      | Ryzen 7 7700 / 9700X     | RX 7900 XTX / 7900 XT     | 24GB VRAM  | 50-75 tokens/s   | Best choice    |
+| High Performance | Ryzen 9 7950X / 9950X    | RX 7900 XTX               | 24GB+ VRAM | 65-90 tokens/s   | Excellent      |
+| Enterprise       | EPYC 7003/9004 series    | MI300X or 2x RX 7900 XTX  | 48GB+ VRAM | 90-140 tokens/s  | For 32B model  |
+| Budget Option    | Ryzen 5 7600 / 9600X     | RX 7800 XT (16GB)         | 16GB VRAM  | 35-50 tokens/s   | Acceptable     |
 
-### Important Memory Notes
+## Important Memory Notes
 
-Even though the 7B INT8 model itself takes approximately **8–9 GB**, we recommend **at least 24GB VRAM** for the following reasons:
+Even though the 7B INT8 model itself takes approximately 8–9 GB, we recommend at least 24GB VRAM for the following reasons:
 
-- KV-cache consumption during generation (especially with long context)
+- KV-cache consumption during generation, especially with long context
 - ONNX Runtime overhead and temporary buffers
-- System stability and to avoid Out of Memory errors
+- System stability and avoiding out-of-memory errors
 - Room for larger context windows
 
 **Minimum recommended:** 24GB VRAM (RX 7900 series)  
 **Ideal:** 24–32GB VRAM
 
-For pure CPU inference (no GPU), we recommend at least **64GB system RAM** (Ryzen 9 7950X/9950X).
+For pure CPU inference (no GPU), we recommend at least 64GB system RAM (Ryzen 9 7950X/9950X).
 
----
 I added the default model in full FP32 precision, which is approximately 62 GB in size. This serves as the base for quantization, allowing us to find the optimal balance between model size and performance.
 
-
 ## 📧 Contact & Licensing
-For joint venture opportunities, hardware integration, or licensing inquiries:
-- **Email:** [grabko@cmsmanhattan.com](mailto:grabko@cmsmanhattan.com)
-- **Phone:** +1 (516) 777-0945
-- **Location:** New York, USA
 
+For joint venture opportunities, hardware integration, or licensing inquiries:
 
+- **Email:** grabko@cmsmanhattan.com
+- **Phone:** +1 (516) 777-0945
+- **Location:** New York, USA