---
license: mit
model-index:
- name: bactrian-x-llama-13b-merged
  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: 56.4
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=haonan-li/bactrian-x-llama-13b-merged
      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: 79.33
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=haonan-li/bactrian-x-llama-13b-merged
      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: 48.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=haonan-li/bactrian-x-llama-13b-merged
      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: 48.38
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=haonan-li/bactrian-x-llama-13b-merged
      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: 73.95
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=haonan-li/bactrian-x-llama-13b-merged
      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: 5.53
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=haonan-li/bactrian-x-llama-13b-merged
      name: Open LLM Leaderboard
---

#### Current Training Steps: 108,000


This repo contains a merged model using low-rank adaptation (LoRA) for LLaMA-13b 
fit on the [Stanford-Alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca)
and [databricks-dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data) data in 52 languages.

### Dataset Creation

1. English Instructions: The English instuctions are obtained from [alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca), and [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data).
2. Instruction Translation: The instructions (and inputs) are translated into the target languages using Google Translation API (conducted on April 2023).
3. Output Generation: We generate output from `gpt-3.5-turbo` for each language (conducted on April 2023).

<h3 align="center">
<img src="https://raw.githubusercontent.com/fajri91/eval_picts/master/BactrianX_dataset.jpg" width="950" align="center">
</h3>

### Training Parameters

The code for training the model is provided in our [github](https://github.com/mbzuai-nlp/Bactrian-X), which is adapted from [Alpaca-LoRA](https://github.com/tloen/alpaca-lora).
This version of the weights was trained with the following hyperparameters:


- Epochs: 10
- Batch size: 128
- Cutoff length: 512
- Learning rate: 3e-4
- Lora _r_: 64
- Lora target modules: q_proj, k_proj, v_proj, o_proj


That is:

```
python finetune.py \
    --base_model='decapoda-research/llama-13b-hf' \
    --num_epochs=5 \
    --batch_size=128 \
    --cutoff_len=512 \
    --group_by_length \
    --output_dir='./bactrian-x-llama-13b-lora' \
    --lora_target_modules='q_proj,k_proj,v_proj,o_proj' \
    --lora_r=64 \
    --micro_batch_size=32
```

Instructions for running it can be found at https://github.com/MBZUAI-nlp/Bactrian-X.

### Discussion of Biases

(1) Translation bias; (2) Potential English-culture bias in the translated dataset.


### Citation Information

```
@misc{li2023bactrianx,
      title={Bactrian-X : A Multilingual Replicable Instruction-Following Model with Low-Rank Adaptation}, 
      author={Haonan Li and Fajri Koto and Minghao Wu and Alham Fikri Aji and Timothy Baldwin},
      year={2023},
      eprint={2305.15011},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```

# [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_haonan-li__bactrian-x-llama-13b-merged)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |52.00|
|AI2 Reasoning Challenge (25-Shot)|56.40|
|HellaSwag (10-Shot)              |79.33|
|MMLU (5-Shot)                    |48.40|
|TruthfulQA (0-shot)              |48.38|
|Winogrande (5-shot)              |73.95|
|GSM8k (5-shot)                   | 5.53|