Update README.md

README.md

@@ -1,28 +1,65 @@
 ---
 license: apache-2.0
 language:
-- en
-- zh
+  - zh
+  - en
+tags:
+  - manufacturing
+  - process-planning
+  - machining
+  - industrial-ai
+  - multimodal
+  - safetensors
+  - qwen3_5
 base_model:
-- Qwen/Qwen3.5-9B
+  - Qwen/Qwen3.5-9B
+pipeline_tag: image-text-to-text
 ---
-## What this model is for:
-This project is an intelligent manufacturing process generation system based on multi-modal large language models. 
-It aims to automatically generate process sequences and machining steps by analyzing manufacturing drawings.
 
+# LevelField-1: Open-Source Manufacturing Process Planning Model
 
+**LevelField-1** is the first open-source large language model purpose-built for **non-standard machining process planning**. Given a 2D manufacturing drawing (PDF/PNG), it interprets part geometry, tolerances, surface roughness, and other technical specifications — then generates complete process routes with optimization suggestions.
 
-## How to use me:
-Make sure you have `vllm>=0.19.1` installed.
-Check if your server has computation force at least with 1 H100.
-The model runs good on Nvidia 12.9 in our lab.
+Built on the Qwen3.5-9B open-source base, fine-tuned and reinforced with 100,000 manufacturing drawings and process sheets from 16 factories. Data construction and result validation completed jointly by the Level AI engineering team and 36 process engineers with 20+ years of hands-on experience.
+
+- **Parameters:** 9B (BF16)
+- **Format:** Merged weights in safetensors (~20GB), full inference files included
+- **License:** Apache 2.0 — free for commercial use
+- **Developer:** [Level AI (蓝沃AI)](https://www.level-ai.cn)
+
+## Capabilities
+
+| Capability | Description |
+|---|---|
+| **Drawing Interpretation** | Input a 2D manufacturing drawing (PDF/PNG). The model reads and organizes part name, drawing number, material, dimensions & tolerances, surface roughness, and other technical requirements. |
+| **Process Route Generation** | Based on the verified machining requirements, the model derives machining steps, rules out unsuitable processes, and outputs a complete process route with optimization suggestions. |
+| **Process Coverage** | Supports 18 common machining process types: turning, milling, drilling, grinding, casting, forging, heat treatment, welding, and more. |
+
+## Key Results
+
+- In internal evaluation, the model's process reasoning achieved **95%+ alignment** with decisions made by senior process engineers.
+- In pilot customer usage, process route drafting time was reduced by approximately **60%**.
+
+> [TODO — 算法团队] Add 1-2 sentences on the evaluation setup: test set size, evaluation criteria, annotator profile. Does not need to be a full benchmark table.
+
+## Quickstart
+
+### Online Demo (no deployment needed)
+
+👉 **[https://smartaps.level-ai.cn/levelField](https://smartaps.level-ai.cn/levelField)**
+
+### Deploy with vLLM
+
+**Requirements:**
+- `vllm >= 0.19.1`
+- Minimum 1× H100 GPU
+- Tested on NVIDIA CUDA 12.9
 
-Then run the script:
 ```bash
 CUDA_VISIBLE_DEVICES=0 \
 OMP_NUM_THREADS=1 \
 vllm serve \
-    /the/local/path/to/the/model/ \
+    /path/to/LevelField/ \
     --port 18124 \
     --served-model-name LevelField \
     --reasoning-parser qwen3 \
@@ -31,4 +68,3 @@ vllm serve \
     --max-model-len 32768 \
     --gpu-memory-utilization 0.9 \
     --mm-processor-cache-type shm
-```