Hugging Face's logo

open-thoughts
/
OpenThinker2-7B

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
2
sedrickkeh commited on
Commit
bd788c5
·
verified ·
1 Parent(s): d8d95d0

update table

Browse files
Files changed (1) hide show
  1. README.md +7 -8
README.md CHANGED
@@ -26,14 +26,13 @@ The [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B) mode
26
  This model improves upon our previous [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) model, which was trained on 114k examples from [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k).
27
  The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).
28
 
29
- | Model | Open Data? | Avg | AIME24 | AIME25 | AMC23 | MATH500 | GPQA-D | LCBv2 |
30
- | ---------------- | ----- | ---- | ------ | ------ | ----- | ------- | ------ | ----- |
31
- | OpenThinker-7B | ✅ | 48.9 | 31.3 | 23.3 | 74.5 | 83.2 | 42.9 | 38.0 |
32
- | OpenThinker2-7B | ✅ | 61.0 | 50.0 | 33.3 | 89.5 | 88.4 | 49.3 | 55.6 |
33
- | R1-Distill-7B | ❌ | 61.3 | 57.3 | 33.3 | 92.0 | 89.6 | 47.3 | 48.4 |
34
- | OlympicCoder-7B | ✅ | 42.4 | 20.7 | 15.3 | 63.0 | 74.8 | 25.3 | 55.4 |
35
- | OpenR1-7B | ✅ | 48.4 | 48.7 | 34.7 | 88.5 | 87.8 | 21.2 | 9.5 |
36
-
37
 
38
  ## Data
39
 
 
26
  This model improves upon our previous [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) model, which was trained on 114k examples from [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k).
27
  The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).
28
 
29
+ | Model | Data | AIME24 | AIME25 | AMC23 | MATH500 | GPQA-D | LCBv2 |
30
+ | --------------------------------------------------------------------------------------------- | ---- | ------ | ------ | ----- | ------- | ------ | ----------- |
31
+ | [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B) | ✅ | 50.0 | 33.3 | 89.5 | 88.4 | 49.3 | 55.6 |
32
+ | [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) | ✅ | 31.3 | 23.3 | 74.5 | 83.2 | 42.9 | 38.0 |
33
+ | [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | ❌ | 57.3 | 33.3 | 92.0 | 89.6 | 47.3 | 48.4 |
34
+ | [OlympicCoder-7B](https://huggingface.co/open-r1/OlympicCoder-7B) | ✅ | 20.7 | 15.3 | 63.0 | 74.8 | 25.3 | 55.4 |
35
+ | [OpenR1-Qwen-7B](https://huggingface.co/open-r1/OpenR1-Qwen-7B) | ✅ | 48.7 | 34.7 | 88.5 | 87.8 | 21.2 | 9.5<br><br> |
 
36
 
37
  ## Data
38