Add pipeline tag, arxiv metadata and fix usage snippets (#1)

- Add pipeline tag, arxiv metadata and fix usage snippets (edc44d3c98e87f7a1b7bba86acab72f8656f409a)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: Qwen/Qwen3-32B
 language:
 - en
 license: apache-2.0
@@ -11,8 +12,9 @@ tags:
 - qwen
 - llm
 - compression
-base_model: Qwen/Qwen3-32B
 base_model_relation: quantized
+pipeline_tag: text-generation
+arxiv: 2509.22944
 ---
 
 <p align="center">
@@ -25,6 +27,9 @@ base_model_relation: quantized
 # A-SINQ 4-bit Quantized Qwen3-32B model
 
 This repository contains the official **4-bit quantized** version of the [`Qwen3-32B`](https://huggingface.co/Qwen/Qwen3-32B) model using the *calibrated* version of **SINQ (Sinkhorn-Normalized Quantization)** method.  
+
+The method was introduced in the paper [SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights](https://huggingface.co/papers/2509.22944) by Lorenz K. Müller, Philippe Bich, Jiawei Zhuang, Ahmet Çelik, Luca Benfenati, and Lukas Cavigelli.
+
 SINQ is a novel, fast and high-quality quantization method designed to make any Large Language Models smaller while keeping their accuracy almost intact. 
 
 To support the project please put a star ⭐ in the official [SINQ](https://github.com/huawei-csl/SINQ) github repository. 
@@ -48,7 +53,7 @@ To support the project please put a star ⭐ in the official [SINQ](https://gith
 
 ---
 
-# 🚀 Usage</span>
+# 🚀 Usage
 
 ## Prerequisite
 Before running the quantization script, make sure the **SINQ** library is installed.
@@ -58,6 +63,7 @@ Installation instructions and setup details are available in the [SINQ official
 You can load and use the model with our wrapper based on the 🤗 Transformers library:
 
 ```python
+import torch
 from transformers import AutoTokenizer
 from sinq.patch_model import AutoSINQHFModel
 
@@ -83,6 +89,7 @@ print(tokenizer.decode(out_ids[0], skip_special_tokens=True))
 The quantized model was obtained using the **SINQ** quantization library, following the steps below:
 
 ```python
+import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from sinq.patch_model import AutoSINQHFModel
 from sinq.sinqlinear import BaseQuantizeConfig