Hugging Face's logo

EQUES
/
OpenRS3-GRPO-ja

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
stardust-eques commited on
Commit
a1ac604
·
verified ·
1 Parent(s): 5f53959

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -3,7 +3,7 @@ base_model: SakanaAI/TinySwallow-1.5B-Instruct
3
  datasets:
4
  - kunishou/OpenMathInstruct-1-1.8m-ja
5
  library_name: transformers
6
- model_name: OpenRS-GRPO-ja
7
  tags:
8
  - generated_from_trainer
9
  - open-r1
@@ -12,7 +12,7 @@ tags:
12
  licence: license
13
  ---
14
 
15
- # Model Card for OpenRS-GRPO-ja
16
 
17
  This model is a fine-tuned version of [SakanaAI/TinySwallow-1.5B-Instruct](https://huggingface.co/SakanaAI/TinySwallow-1.5B-Instruct) on the [kunishou/OpenMathInstruct-1-1.8m-ja](https://huggingface.co/datasets/kunishou/OpenMathInstruct-1-1.8m-ja/viewer/default/train?row=0&views%5B%5D=train) dataset.
18
  It has been trained using [TRL](https://github.com/huggingface/trl).
 
3
  datasets:
4
  - kunishou/OpenMathInstruct-1-1.8m-ja
5
  library_name: transformers
6
+ model_name: OpenRS3-GRPO-ja
7
  tags:
8
  - generated_from_trainer
9
  - open-r1
 
12
  licence: license
13
  ---
14
 
15
+ # Model Card for OpenRS3-GRPO-ja
16
 
17
  This model is a fine-tuned version of [SakanaAI/TinySwallow-1.5B-Instruct](https://huggingface.co/SakanaAI/TinySwallow-1.5B-Instruct) on the [kunishou/OpenMathInstruct-1-1.8m-ja](https://huggingface.co/datasets/kunishou/OpenMathInstruct-1-1.8m-ja/viewer/default/train?row=0&views%5B%5D=train) dataset.
18
  It has been trained using [TRL](https://github.com/huggingface/trl).