You can deploy this model and start earning money today!

RichardErkhov/
Unbabel_-_TowerBase-7B-v0.1-gguf

Name: Unbabel_-_TowerBase-7B-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TowerBase-7B-v0.1 - GGUF

Model creator: https://huggingface.co/Unbabel/
Original model: https://huggingface.co/Unbabel/TowerBase-7B-v0.1/

Name	Quant method	Size
TowerBase-7B-v0.1.Q2_K.gguf	Q2_K	2.36GB
TowerBase-7B-v0.1.IQ3_XS.gguf	IQ3_XS	2.6GB
TowerBase-7B-v0.1.IQ3_S.gguf	IQ3_S	2.75GB
TowerBase-7B-v0.1.Q3_K_S.gguf	Q3_K_S	2.75GB
TowerBase-7B-v0.1.IQ3_M.gguf	IQ3_M	2.9GB
TowerBase-7B-v0.1.Q3_K.gguf	Q3_K	3.07GB
TowerBase-7B-v0.1.Q3_K_M.gguf	Q3_K_M	3.07GB
TowerBase-7B-v0.1.Q3_K_L.gguf	Q3_K_L	3.35GB
TowerBase-7B-v0.1.IQ4_XS.gguf	IQ4_XS	3.4GB
TowerBase-7B-v0.1.Q4_0.gguf	Q4_0	3.56GB
TowerBase-7B-v0.1.IQ4_NL.gguf	IQ4_NL	3.58GB
TowerBase-7B-v0.1.Q4_K_S.gguf	Q4_K_S	3.59GB
TowerBase-7B-v0.1.Q4_K.gguf	Q4_K	3.8GB
TowerBase-7B-v0.1.Q4_K_M.gguf	Q4_K_M	3.8GB
TowerBase-7B-v0.1.Q4_1.gguf	Q4_1	3.95GB
TowerBase-7B-v0.1.Q5_0.gguf	Q5_0	4.33GB
TowerBase-7B-v0.1.Q5_K_S.gguf	Q5_K_S	4.33GB
TowerBase-7B-v0.1.Q5_K.gguf	Q5_K	4.45GB
TowerBase-7B-v0.1.Q5_K_M.gguf	Q5_K_M	4.45GB
TowerBase-7B-v0.1.Q5_1.gguf	Q5_1	4.72GB
TowerBase-7B-v0.1.Q6_K.gguf	Q6_K	5.15GB

Original model description:

license: cc-by-nc-4.0 language:

en
de
fr
zh
pt
nl
ru
ko
it
es 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.

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, 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 and bilingual data from various sources (e.g., OPUS).

Citation

bibtex

@misc{tower_llm_2024,
      title={Tower: An Open Multilingual Large Language Model for Translation-Related Tasks}, 
      author={Duarte M. Alves and José Pombal and Nuno M. Guerreiro and Pedro H. Martins and João Alves and Amin Farajian and Ben Peters and Ricardo Rei and Patrick Fernandes and Sweta Agrawal and Pierre Colombo and José G. C. de Souza and André F. T. Martins},
      year={2024},
      eprint={2402.17733},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

RichardErkhov/Unbabel_-_TowerBase-7B-v0.1-gguf