---
language:
- en
license: cc-by-nc-sa-4.0
datasets:
- kyujinpy/orca_math_dpo
pipeline_tag: text-generation
model-index:
- name: Sakura-SOLRCA-Math-Instruct-DPO-v2
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 71.25
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 88.52
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 66.13
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 72.16
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 83.03
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 63.91
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
      name: Open LLM Leaderboard
---

# **Sakura-SOLRCA-Math-Instruct-DPO-v2**  
<img src='./sakura.png' width=512>

## Model Details

**Model Developers** Kyujin Han (kyujinpy)

**Method**  
Using DPO method.  
With [Intel/orca_dpo_pairs](https://huggingface.co./datasets/Intel/orca_dpo_pairs) and [argilla/distilabel-math-preference-dpo](https://huggingface.co./datasets/argilla/distilabel-math-preference-dpo).  

I shared the merge version [kyujinpy/orca_math_dpo](https://huggingface.co./datasets/kyujinpy/orca_math_dpo).  
     
I shared the information about my model. (training and code)  
Please see: ⭐[Sakura-SOLAR](https://github.com/KyujinHan/Sakura-SOLAR-DPO).  

# **Model Benchmark**  

## Open leaderboard
- Follow up as [link](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard).  

| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Sakura-SOLRCA-Math-Instruct-DPO-v2 | 74.17 | 71.25 | 88.52 | 66.13 | 72.16 | 83.03 | 63.91 |
| Sakura-SOLRCA-Math-Instruct-DPO-v1 | 74.13 | 71.25 | 88.48 | 66.21 | 72.12 | 82.87 | 63.84 |
| Sakura-SOLRCA-Instruct-DPO | 74.05 | 71.16 | 88.49 | 66.17 | 72.10 | 82.95 | 63.46 |
| Sakura-SOLAR-Instruct-DPO-v2 | 74.14 | 70.90 | 88.41 | 66.48 | 71.86 | 83.43 | 63.76 |
| [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co./kyujinpy/Sakura-SOLAR-Instruct) | 74.40 | 70.99 | 88.42 | 66.33 | 71.79 | 83.66 | 65.20 |

   
# Implementation Code
```python
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```

---
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co./datasets/open-llm-leaderboard/details_kyujinpy__Sakura-SOLRCA-Math-Instruct-DPO-v2)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |74.17|
|AI2 Reasoning Challenge (25-Shot)|71.25|
|HellaSwag (10-Shot)              |88.52|
|MMLU (5-Shot)                    |66.13|
|TruthfulQA (0-shot)              |72.16|
|Winogrande (5-shot)              |83.03|
|GSM8k (5-shot)                   |63.91|