clean up model card: fix numbering, typos, and code examples

- add section numbers 1-8 and remove duplicate 6.2 SGLang heading
- add Pricing section with token pricing table
- fix garbled --enable-auto-tool-choice flag in vLLM bf16 block
- swap served-model-name between fp8 and bf16 examples
- fix Python syntax error (newline inside string) in chat example
- rewrite 5.2 example in Python OpenAI client style to match 5.1
- fix undefined tokenizer reference in Transformers example
- correct JSON code fence and clarify unified memory wording
- expand YAML frontmatter with library_name, pipeline_tag, language, tags

README.md

@@ -1,12 +1,22 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+language:
+  - en
+tags:
+  - vision-language
+  - multimodal
+  - moe
 ---
 
-## Introduction
+## 1. Introduction
+
 Step 3.7 Flash is a 198B-parameter Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding. Engineered for high-frequency production workloads, it activates approximately 11B parameters per token and delivers a throughput of up to 400 tokens per second. Step 3.7 Flash supports a 256k context window and offers three selectable reasoning levels (low, medium, and high) so developers can easily balance speed, cost, and cognitive depth.
+
 We built Step 3.7 Flash for developers who need to scale agentic workflows that combine perception, search, and reasoning. It is designed to handle intensive tasks such as parsing massive financial reports in one pass, running multi-step search loops with cross-source verification, or operating concurrent coding agents in high-throughput pipelines.
 
-## Capabilities & Performance
+## 2. Capabilities & Performance
 
 ### Multimodal Perception and Verification
 
@@ -22,16 +32,22 @@ Step 3.7 Flash is built for live engineering tasks and secured a definitive seco
 
 ## 3. Pricing
 
+| Token Type | Price |
+|---|---|
+| Input (cache miss) | $0.20 / M tokens |
+| Input (cache hit) | $0.04 / M tokens |
+| Output | $1.15 / M tokens |
+
 ## 4. Availability, Deployment, and Ecosystem
 - Availability: Step 3.7 Flash is available through StepFun Open Platform at platform.stepfun.ai and platform.stepfun.com, as well as partner platforms including OpenRouter and NVIDIA NIM.
 - Deployment: Step 3.7 Flash supports flexible deployment across cloud, data center, and local environments. For large-scale production and enterprise use cases, Step 3.7 Flash can be deployed on modern data center infrastructure. For local and workstation scenarios, it can also run on high-memory devices such as NVIDIA DGX Station, AMD Ryzen AI Max+ 395-based systems, and Mac Studio / Macbook Pro devices with at least 128GB unified memory.
 - Ecosystem: Step 3.7 Flash is supported across popular open-source infrastructure for both inference and model development. For inference and serving, developers can use vLLM, SGLang, Hugging Face Transformers, and llama.cpp. For model development workflows, StepFun model support has landed in the NVIDIA Megatron ecosystem, including Megatron Core and Megatron Bridge.
 
-## 5. Examples 
+## 5. Examples
 
 You can get started with Step 3.7 Flash in minutes using StepFun's API or via other inference providers.
 
-5.1  Chat Example
+### 5.1 Chat Example
 
 ```python
 from openai import OpenAI
@@ -43,8 +59,7 @@ completion = client.chat.completions.create(
     messages=[
         {
             "role": "system",
-            "content":"You are an AI assistant provided by StepFun. You are good at Chinese, English, and many other languages, and you can see, think, and act to 
-help users get things done.",
+            "content": "You are an AI assistant provided by StepFun. You are good at Chinese, English, and many other languages, and you can see, think, and act to help users get things done.",
         },
         {
             "role": "user",
@@ -59,33 +74,34 @@ print(completion)
 ### 5.2 Text and Image Input Example
 
 ```python
-{                                                                                                                     
-    "model": "step-3.7-flash",                                                                                                  
-    "messages": [                                                                                                       
-      {                                                                                                                 
-        "role": "user",                                                                                                 
-        "content": [                                                                                                    
-          {                                                                                                             
-            "type": "text",                                                                                             
-            "text": "what is in this picture?"                                                                                
-          },                                                                                                            
-          {                                                                                                             
-            "type": "image_url",                                                                                        
-            "image_url": {                                                                                              
-              "url": "https://example.com/photo.jpg"                                                                    
-            }                                                                                                           
-          }                                                                                                             
-        ]                                                                                                               
-      }                                                                                                                 
-    ]
-  }
+from openai import OpenAI
+
+client = OpenAI(api_key="STEP_API_KEY", base_url="https://api.stepfun.com/v1")
+
+completion = client.chat.completions.create(
+    model="step-3.7-flash",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What is in this picture?"},
+                {
+                    "type": "image_url",
+                    "image_url": {"url": "https://example.com/photo.jpg"},
+                },
+            ],
+        },
+    ],
+)
+
+print(completion)
 ```
 
 ## 6. Local Deployment
 
 Step 3.7 Flash is optimized for local inference and supports industry-standard backends including vLLM, SGLang, Hugging Face Transformers and llama.cpp.
 
-### 6.1 vLLM 
+### 6.1 vLLM
 
 We recommend using the latest nightly build of vLLM.
 
@@ -106,7 +122,7 @@ pip install -U vllm --pre \
   - For fp8 model
   ```bash
   vllm serve <MODEL_PATH_OR_HF_ID> \
-  --served-model-name step3p7-flash \
+  --served-model-name step3p7-flash-fp8 \
   --tensor-parallel-size 8 \
   --enable-expert-parallel \
   --disable-cascade-attn \
@@ -114,17 +130,17 @@ pip install -U vllm --pre \
   --enable-auto-tool-choice \
   --tool-call-parser step3p5 \
   --speculative_config '{"method": "mtp", "num_speculative_tokens": 3}' \
-  --trust-remote-code     
+  --trust-remote-code
   ```
   - For bf16 model
   ```bash
   vllm serve <MODEL_PATH_OR_HF_ID> \
-  --served-model-name step3p7-flash-fp8 \
+  --served-model-name step3p7-flash \
   --tensor-parallel-size 8 \
   --enable-expert-parallel \
   --disable-cascade-attn \
   --reasoning-parser step3p5 \
-  --enab        -     -auto-tool-choice \
+  --enable-auto-tool-choice \
   --tool-call-parser step3p5 \
   --speculative_config '{"method": "mtp", "num_speculative_tokens": 3}' \
   --trust-remote-code
@@ -153,9 +169,6 @@ pip install -U vllm --pre \
 
 ### 6.2 SGLang
 
-
-### 6.2 SGLang
-
 1. Install SGLang.
 
 ```bash
@@ -247,7 +260,7 @@ inputs = processor.apply_chat_template(
 
 # 3. Generate
 generated_ids = model.generate(**inputs, max_new_tokens=128, do_sample=False)
-output_text = tokenizer.decode(generated_ids[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+output_text = processor.tokenizer.decode(generated_ids[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
 
 print(output_text)
 ```
@@ -266,7 +279,7 @@ GGUF Model Weights:
 | Multimodal Projector | FP16 | 3.97 GB |
 
 - **Runtime Overhead:** ~7 GB
-- **Minimum VRAM:** 120 GB (e.g., Mac Studio, NVIDIA DGX Station, AMD Ryzen AI Max+ 395)
+- **Minimum unified memory / VRAM:** 120 GB (e.g., Mac Studio, NVIDIA DGX Station, AMD Ryzen AI Max+ 395)
 - **Recommended:** 128 GB unified memory
 
 **Steps**