Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: transformers
-license: other
+license: apache-2.0
 base_model: Qwen/Qwen2.5-32B-Instruct
 tags:
 - llama-factory
@@ -9,28 +9,37 @@ tags:
 model-index:
 - name: original
   results: []
+language:
+- en
+datasets:
+- bespokelabs/Bespoke-Stratos-17k
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# original
-
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the Stratos-R1 dataset.
+<p align="center">
+    <img src="https://huggingface.co/bespokelabs/Bespoke-MiniCheck-7B/resolve/main/Bespoke-Labs-Logo.png" width="550">
+</p>
 
 ## Model description
-
-More information needed
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the [Bespoke-Stratos-17k dataset](https://huggingface.co/datasets/bespokelabs/Bespoke-Stratos-17k).
+The dataset is derived by distilling DeepSeek-R1 using the data pipeline of Berkeley NovaSky’s Sky-T1 with some modifications. More info in the dataset card at [Bespoke-Stratos-17k](https://huggingface.co/datasets/Bespoke-Stratos-17k).
+It outperforms Qwen-2.5-7B-Instruct on reasoning benchmarks:
+
+| Metric | Bespoke-Stratos-32B | Sky-T1-32B | O1-preview | DeepSeek-R1 | DeepSeek-R1-Distill-Qwen-32B |
+|---------|-------------------|-------------|------------|------------|----------------------------|
+| AIME2024 | 56.7 | 43.3 | 40.0 | 79.8 | 72.6 |
+| MATH500 | 92.4 | 82.4 | 81.4 | 97.3 | 94.3 |
+| GPQA-Diamond | 55.6 | 56.8 | 75.2 | 71.5 | 62.1 |
+| LiveCodeBench Easy | 93.4 | 86.3 | 92.9 | - | - |
+| LiveCodeBench Medium | 60.7 | 56.8 | 54.9 | - | - |
+| LiveCodeBench Hard | 24.4 | 17.9 | 16.3 | - | - |
+| LiveCodeBench All | 63.60 | 57.93 | 59.13 | 65.9 | 57.2 |
 
 ## Intended uses & limitations
 
-More information needed
-
-## Training and evaluation data
-
-More information needed
+Non-commercial use.
 
 ## Training procedure
+We used 8xH100 to train the model for 27 hours.
 
 ### Training hyperparameters
 
@@ -58,4 +67,4 @@ The following hyperparameters were used during training:
 - Transformers 4.46.1
 - Pytorch 2.5.1+cu124
 - Datasets 3.1.0
-- Tokenizers 0.20.3
+- Tokenizers 0.20.3