Add paper link and sample usage for Fill-in-the-Middle (FIM)

Hi! I'm Niels from the Hugging Face community science team. I've opened this pull request to improve your model card.

Based on the official GitHub repository and the technical report, I've added a link to the paper and included a sample usage code snippet for the "Fill-in-the-Middle" (FIM) task. FIM is a key feature for code base models, allowing them to complete code given both a prefix and a suffix.

README.md

@@ -7,6 +7,9 @@ pipeline_tag: text-generation
 
 # Qwen3-Coder-Next-Base
 
+## Introduction
+**Qwen3-Coder-Next-Base** is an open-weight language model designed specifically for coding agents and local development. It is the base version of the 80B parameter model that activates only 3B parameters during inference, as described in the [Qwen3-Coder-Next Technical Report](https://huggingface.co/papers/2603.00729).
+
 ## Highlights
 
 Today, we're announcing **Qwen3-Coder-Next-Base**, an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:  
@@ -45,6 +48,43 @@ Today, we're announcing **Qwen3-Coder-Next-Base**, an open-weight language model
 
 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwen.ai/blog?id=qwen3-coder-next), [GitHub](https://github.com/QwenLM/Qwen3-Coder), and [Documentation](https://qwen.readthedocs.io/en/latest/).
 
+## Sample Usage
+
+### Fill in the middle with Qwen3-Coder
+
+The code insertion task, also referred to as the "fill-in-the-middle" challenge, requires the insertion of code segments in a manner that bridges the gaps within a given code context. 
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "Qwen/Qwen3-Coder-Next-Base"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto").eval()
+
+input_text = """<|fim_prefix|>def quicksort(arr):
+    if len(arr) <= 1:
+        return arr
+    pivot = arr[len(arr) // 2]
+    <|fim_suffix|>
+    middle = [x for x in arr if x == pivot]
+    right = [x for x in arr if x > pivot]
+    return quicksort(left) + middle + quicksort(right)<|fim_middle|>"""
+            
+model_inputs = tokenizer([input_text], return_tensors="pt").to(model.device)
+
+# Use `max_new_tokens` to control the maximum output length.
+# FIM specific special tokens:
+eos_token_ids = [151659, 151661, 151662, 151663, 151664, 151643, 151645]
+generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512, do_sample=False, eos_token_id=eos_token_ids)[0]
+
+# The generated_ids include prompt_ids, we only need to decode the tokens after prompt_ids.
+output_text = tokenizer.decode(generated_ids[len(model_inputs.input_ids[0]):], skip_special_tokens=True)
+
+print(f"Prompt: {input_text}
+
+Generated text: {output_text}")
+```
+
 ## Best Practices
 
 To achieve optimal performance, we recommend the following sampling parameters: `temperature=1.0`, `top_p=0.95`, `top_k=40`.
@@ -54,7 +94,7 @@ To achieve optimal performance, we recommend the following sampling parameters:
 
 If you find our work helpful, feel free to give us a cite.
 
-```
+```bibtex
 @techreport{qwen_qwen3_coder_next_tech_report,
   title        = {Qwen3-Coder-Next Technical Report},
   author       = {{Qwen Team}},