Add pipeline tag and usage examples

README.md

@@ -1,7 +1,9 @@
 ---
+base_model: Qwen/Qwen2.5-32B-Instruct
+datasets:
+- open-thoughts/OpenThoughts2-1M
 library_name: transformers
 license: apache-2.0
-base_model: Qwen/Qwen2.5-32B-Instruct
 tags:
 - llama-factory
 - full
@@ -9,8 +11,7 @@ tags:
 model-index:
 - name: OpenThinker2-32B
   results: []
-datasets:
-- open-thoughts/OpenThoughts2-1M
+pipeline_tag: text-generation
 ---
 
 <p align="center">
@@ -20,12 +21,11 @@ datasets:
 > [!NOTE]
 > We have released a paper for OpenThoughts! See our paper [here](https://arxiv.org/abs/2506.04178).
 
-# OpenThinker2-32B
+# OpenThinker2-32B: A Powerful Open-Data Reasoning Model
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the 
-[OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.
+OpenThinker2-32B is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) trained on the [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.  This model represents a significant advancement in open-source reasoning capabilities, achieving competitive performance with closed-source models on various benchmarks. OpenThinker2-32B excels at complex reasoning tasks involving math, code, and general knowledge, demonstrating its versatility and robustness.
 
-The [OpenThinker2-32B](https://huggingface.co/open-thoughts/OpenThinker2-32B) model is the highest performing open-data model. 
+The [OpenThinker2-32B](https://huggingface.co/open-thoughts/OpenThinker2-32B) model is the highest performing open-data model.
 This model improves upon our previous [OpenThinker-32B](https://huggingface.co/open-thoughts/OpenThinker-32B) model, which was trained on 114k examples from [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k).
 The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).
 
@@ -38,6 +38,40 @@ The numbers reported in the table below are evaluated with our open-source tool
 | [S1.1-32B](https://huggingface.co/simplescaling/s1.1-32B)                                       | ✅    | 59.3   | 42.7   | 91.5  | 87.4    | 62.0   | 58.7  |
 
 
+## Usage Examples
+
+This model can be easily used with the Hugging Face `pipeline` API for text generation.
+
+**Example 1: Simple Text Generation**
+
+```python
+from transformers import pipeline
+
+generator = pipeline('text-generation', model='open-thoughts/OpenThinker2-32B')
+result = generator("Once upon a time,", max_length=50)
+print(result[0]['generated_text'])
+```
+
+**Example 2: Controlling the Length of the Generated Text**
+
+```python
+from transformers import pipeline
+
+generator = pipeline('text-generation', model='open-thoughts/OpenThinker2-32B')
+result = generator("The quick brown fox jumps over the lazy dog.", max_length=100)
+print(result[0]['generated_text'])
+```
+
+**Example 3: Setting the Temperature**
+
+```python
+from transformers import pipeline
+
+generator = pipeline('text-generation', model='open-thoughts/OpenThinker2-32B')
+result = generator("Write a short poem about nature:", max_length=50, temperature=0.7)
+print(result[0]['generated_text'])
+```
+
 ## Data
 
 This model was trained on the [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.
@@ -85,6 +119,7 @@ More info can be found in our repository: [https://github.com/open-thoughts/open
 - 📝 [OpenThoughts Paper](https://arxiv.org/abs/2506.04178)
 - 📊 [OpenThoughts2 and OpenThinker2 Blog Post](https://www.open-thoughts.ai/blog/thinkagain)
 - 💻 [Open Thoughts GitHub Repository](https://github.com/open-thoughts/open-thoughts)
+- 🌐 [Project Page](https://openthoughts.ai)
 - 🧠 [OpenThoughts2-1M dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M)
 - 🤖 [OpenThinker2-7B model](https://huggingface.co/open-thoughts/OpenThinker2-7B)
 - 🤖 [OpenThinker2-32B model](https://huggingface.co/open-thoughts/OpenThinker2-32B) - this model.
@@ -100,4 +135,4 @@ More info can be found in our repository: [https://github.com/open-thoughts/open
   primaryClass={cs.LG},
   url={https://arxiv.org/abs/2506.04178}, 
 }
-```
+```