README.md

---
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
base_model: jondurbin/bagel-34b-v0.2
model-index:
- name: Smaugv0.1
  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: 74.23
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Smaugv0.1
      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: 86.76
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Smaugv0.1
      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: 76.66
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Smaugv0.1
      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: 70.22
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Smaugv0.1
      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: 83.66
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Smaugv0.1
      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: 72.18
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Smaugv0.1
      name: Open LLM Leaderboard
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/e4u8VYfDBh11u60rFYJHF.png)

This model is a finetune of jondurbin's excellent [bagel](https://huggingface.co/jondurbin/bagel-34b-v0.2) model. This model has not utilised any form of merging.

We created Smaug-34B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). 
We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228.

We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's 
likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases. 
Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode. 
Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.

We believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models.
With the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space!


### Evaluation Results

| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- |
|  77.29  | 74.23 | 86.76  | 76.66 | 70.22 | 83.66 | 72.18 |

### Contamination Results

With reference model jondurbin/bagel-34b-v0.2:

| ARC | TruthfulQA | GSM8K |
| --- | --- | --- |
| 0.08| 0.38| 0.88|

### Citation

Please cite the paper if you use data, model, or method in this repo.

```
@article{pal2024smaug,
  title={Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive},
  author={Pal, Arka and Karkhanis, Deep and Dooley, Samuel and Roberts, Manley and Naidu, Siddartha and White, Colin},
  journal={arXiv preprint arXiv:2402.13228},
  year={2024}
}
```
# [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_abacusai__Smaugv0.1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |77.29|
|AI2 Reasoning Challenge (25-Shot)|74.23|
|HellaSwag (10-Shot)              |86.76|
|MMLU (5-Shot)                    |76.66|
|TruthfulQA (0-shot)              |70.22|
|Winogrande (5-shot)              |83.66|
|GSM8k (5-shot)                   |72.18|