---
language:
- en
- de
- fr
- zh
- pt
- nl
- ru
- ko
- it
- es
license: cc-by-nc-4.0
metrics:
- comet
pipeline_tag: translation
model-index:
- name: TowerBase-7B-v0.1
  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: 51.02
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1
      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: 77.68
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1
      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: 43.48
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1
      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: 37.29
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1
      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: 72.06
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1
      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: 13.12
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Unbabel/TowerBase-7B-v0.1
      name: Open LLM Leaderboard
---
# Model Card for TowerBase-7B-v0.1

## Model Details

### Model Description

TowerBase-7B is a language model that results from continuing the pretraining of Llama 2 on a mix of 20 billion tokens of monolingual data in ten different languages — English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian — and bilingual data. TowerBase-7B-v0.1 is the first model in the series. 
The resulting model shows improved performance on the supported languages, while maintaining Llama 2's capabilities on English. It is particularly well-suited for fine-tuning on translation and related tasks: check out [TowerInstruct](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1).

We will release more details in the upcoming technical report.

- **Developed by:** Unbabel, Instituto Superior Técnico, CentraleSupélec University of Paris-Saclay 
- **Model type:** A 7B parameter model built on top of Llama 2 by continuing pretraining on multilingual data.
- **Language(s) (NLP):** English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian
- **License:** CC-BY-NC-4.0, Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

## Intended uses & limitations

The model is intended for research purposes in the 10 languages it supports.
The model is able to perform well on translation and related tasks (e.g., APE, GEC) on a few-shot regime. 
It can also be fine-tuned to perform these tasks in a zero-shot fashion (see [TowerInstruct](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1), as well as other multilingual tasks.

### Out-of-Scope Use

The model is not guaranteed to perform well for languages other than the 10 languages it supports.

## Bias, Risks, and Limitations

TowerBase-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements). 

## Run the model

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Unbabel/TowerBase-7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)

text = "English: My name is TowerBase.\nPortuguese:"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### Training Data

Filtered versions of [mc4](https://huggingface.co/datasets/mc4) and bilingual data from various sources (e.g., [OPUS](https://opus.nlpl.eu/)).

## Citation 

To be completed.

# [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_Unbabel__TowerBase-7B-v0.1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |49.11|
|AI2 Reasoning Challenge (25-Shot)|51.02|
|HellaSwag (10-Shot)              |77.68|
|MMLU (5-Shot)                    |43.48|
|TruthfulQA (0-shot)              |37.29|
|Winogrande (5-shot)              |72.06|
|GSM8k (5-shot)                   |13.12|