Add text-generation pipeline tag and usage example

This PR adds the missing `pipeline_tag`, ensuring people can find your model at https://huggingface.co/models?pipeline_tag=text-generation. It also adds a usage example.

README.md

@@ -1,15 +1,17 @@
 ---
-license: mit
-language:
-- en
-tags:
-- LLM
-library_name: transformers
 base_model:
 - Qwen/Qwen2.5-32B
 datasets:
 - MiniMaxAI/SynLogic
+language:
+- en
+library_name: transformers
+license: mit
+tags:
+- LLM
+pipeline_tag: text-generation
 ---
+
 # SynLogic Zero-Mix-3: Large-Scale Multi-Domain Reasoning Model
 
 * 🐙 **GitHub Repo:** [https://github.com/MiniMax-AI/SynLogic](https://github.com/MiniMax-AI/SynLogic)
@@ -20,6 +22,22 @@ datasets:
 
 **Zero-Mix-3** is an advanced multi-domain reasoning model trained using Zero-RL (reinforcement learning from scratch) on a diverse mixture of logical reasoning, mathematical, and coding data. Built on Qwen2.5-32B-Base, this model demonstrates the power of combining diverse verifiable reasoning tasks in a unified training framework.
 
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "MiniMaxAI/SynLogic-Mix-3-32B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+
+prompt = "What is 2 + 2?"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
 ## Key Features
 
 * **Multi-Domain Training:** Jointly trained on logical reasoning (SynLogic), mathematics, and coding tasks