QuantFactory / Atlas-Chat-9B-GGUF

QuantFactory/Atlas-Chat-9B-GGUF

This is quantized version of MBZUAI-Paris/Atlas-Chat-9B created using llama.cpp

Original Model Card

Atlas-Chat Model Card

Model Overview

Atlas-Chat is a family of open models instruction-tuned for Darija, the colloquial Arabic of Morocco, developed as part of the Jais project for standard Arabic and its extentions to dialectal Arabic. These models are designed for language generation and excel in various applications such as question answering, summarization, and translation. Thanks to their compact size, Atlas-Chat models can be deployed in resource-constrained environments like laptops, desktops, or personal cloud setups, making advanced AI accessible to Darija speakers and promoting widespread innovation. Two versions are available:

• Atlas-Chat-2B : A small-sized version with 2 billion parameters, capable of generating fluent Moroccan Darija text while maintaining efficiency.
• Atlas-Chat-9B : A larger version with 9 billion parameters, providing more nuanced, contextually rich language generation for complex tasks.

The models are designed to assist with:

• Conversational agents and chatbots that operate in Darija.
• Translation, summarization, and content generation in informal dialect.
• Cultural research related to Morocco and its language.

Paper: Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

👥 Our Team

The model is developed by MBZUAI France Lab, an AI research center in Paris affiliated with the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) headquartered in Abu Dhabi.

Usage

Below we share some code snippets on how to get quickly started with running the model. First, install the Transformers library with:

pip install -U transformers sentencepiece

Then, copy the snippet from the section that is relevant for your use case.

Running with the pipeline API

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="MBZUAI-Paris/Atlas-Chat-9B",
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="cuda" # replace with "mps" to run on a Mac device
)

messages = [
    {"role": "user", "content": 'شكون لي صنعك؟'},
]

outputs = pipe(messages, max_new_tokens=256, temperature=0.0)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)

• Response:

صنعاتني جامعة محمد بن زايد للذكاء الاصطناعي، لي هي جامعة بحثية ديال الدراسات العليا الهدف ديالها أنها تزيد بالذكاء الاصطناعي لقدّام وتنفع بيه الإنسانية. يمكن ليك تزور https://mbzuai.ac.ae/ar/about/ باش تعرف كثر على جامعة محمد بن زايد للذكاء الاصطناعي والمهمة ديالها!

Running the model on a single / multi GPU

pip install accelerate

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "MBZUAI-Paris/Atlas-Chat-9B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

messages = [
    {"role": "user", "content": "شنو كيتسمى المنتخب المغربي ؟"},
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True, , add_generation_prompt=True)

outputs = model.generate(**input_ids, max_new_tokens=256)

print(tokenizer.decode(outputs[0]))

• Response:

  المنتخب المغربي كيتسمى أيضا "أسود الأطلس"

Quantized Versions through bitsandbytes

pip install bitsandbytes accelerate

# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

model_id = "MBZUAI-Paris/Atlas-Chat-9B"
quantization_config = BitsAndBytesConfig(load_in_8bit=True)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    quantization_config=quantization_config,
)
text = f"""
        شرح ليا هاد الهضرة:
        في القرن 19 لقاو الذّهب في كاليفورنيا، ناضو لّي كيبيعو العتلة والفاس كيقنعو الناس بلي غيديرو لاباس يلا قلبو على الذهب... فالأخير اغتنى تجار أدوات التنقيب والحفر. وحاليا كاين لّي كيقنع الأخرين بلي هو مليونير، وعندو الوقت يورّي للآخرين كيفاش يديرو لاباس.
        """
messages = [
    {"role": "user", "content": text},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=256)
print(tokenizer.decode(outputs[0]).split("<start_of_turn>model")[-1])

# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

model_id = "MBZUAI-Paris/Atlas-Chat-9B"
quantization_config = BitsAndBytesConfig(load_in_4bit=True)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    quantization_config=quantization_config,
)
text = f"""ترجم للدارجة:
Atlas Chat is the first open source large language model that talks in Darija.
        """
messages = [
    {"role": "user", "content": text},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True, add_generation_prompt=True)

outputs = model.generate(**input_ids, max_new_tokens=256, temperature=0.0)
print(tokenizer.decode(outputs[0]).split("<start_of_turn>model")[-1])

Chat Template

The models use a chat template that must be adhered to conversational use. The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.

Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "MBZUAI-Paris/Atlas-Chat-9B"
dtype = torch.bfloat16

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda",
    torch_dtype=dtype,)

chat = [
    { "role": "user", "content": "أشنو كايمييز المملكة المغربية." },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

At this point, the prompt contains the following text:

<bos><start_of_turn>user
أشنو كايمييز المملكة المغربية.<end_of_turn>
<start_of_turn>model

As you can see, each turn is preceded by a <start_of_turn> delimiter and then the role of the entity (either user , for content supplied by the user, or model for LLM responses). Turns finish with the <end_of_turn> token.

You can follow this format to build the prompt manually, if you need to do it without the tokenizer's chat template.

After the prompt is ready, generation can be performed like this:

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

• Response:

المغرب كايميزو بزاف ديال الحوايج، منهم:

1. التنوع الثقافي: المغرب بلاد فيها بزاف ديال الثقافات، كل وحدة فيهم عندها التقاليد ديالها واللغة ديالها والماكلة ديالها. هاد التنوع كايبان فالموسيقى والرقص والفنون التقليدية.

2. التراث التاريخي: المغرب عندو تاريخ غني كايمتد لآلاف السنين، فيه حضارات قديمة بحال مملكة موريطانيا، والرومان، والبيزنطيين، والفتوحات الإسلامية. هاد التراث كايبان فالمعالم التاريخية بحال مدينة فاس، والمدينة القديمة ديال مراكش، والمدينة القديمة ديال شفشاون.

3. المناظر الطبيعية: المغرب بلاد فيها مناظر طبيعية متنوعة، من السواحل الزرقة والصحاري الكبيرة، للجبال العالية والوديان الخضراء. هاد التنوع كايمكنك من ممارسة أنشطة خارجية بحال المشي لمسافات طويلة، والتخييم، والرياضات المائية.

4. الماكلة: الماكلة المغربية معروفة بالتنوع ديالها والطعم ديالها. من بين الأطباق الأكثر شعبية كاين الطاجين، والكسكس، والبريوات، والكوكتيل ديال الفواكه.

5. الناس: المغاربة معروفين بالضيافة ديالهم والترحاب ديالهم. كايكونو فرحانين باش يشاركو الثقافة والتقاليد ديالهم مع الزوار.

Inputs and outputs

• Input: Text string, such as a question, a prompt, or a document to be summarized.
• Output: Generated Darija text in response to the input, such as an answer to a question, or a summary of a document.

Chatbot interface using Ollama

You can also use Ollama and chatbot-ollama to create a chatbot user-interface to better test the model. First you need to install Ollama on your machine from here and have node.js installed as well. Then, download and prepare the model as follows:

huggingface-cli download MBZUAI-Paris/Atlas-Chat-9B --local-dir Atlas-Chat-9B/
ollama create Atlas-Chat-9B -f Atlas-Chat-9B/modelfile
ollama serve

Finally, in a new terminal clone chatbot-ollama repository from Github and run it:

git clone https://github.com/ivanfioravanti/chatbot-ollama.git
cd chatbot-ollama
npm ci
npm run dev

You can start chatting with the model by visiting http://localhost:3000 .

Citation

If you use Atlas-Chat in your research, please cite our paper:

@article{shang2024atlaschatadaptinglargelanguage,
      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect}, 
      author={Guokan Shang and Hadi Abdine and Yousef Khoubrane and Amr Mohamed and Yassine Abbahaddou and Sofiane Ennadir and Imane Momayiz and Xuguang Ren and Eric Moulines and Preslav Nakov and Michalis Vazirgiannis and Eric Xing},
      year={2024},
      eprint={2409.17912},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2409.17912}, 
}

Training Data

The model was trained on diverse datasets focusing on Darija consisting for approximatley 450k instructions of a maximum length of 2048 tokens, including:

• Synthetic instructions created to guide the model in processing various types of language tasks tailord towards Moroccan culture.
• Instruction samples created from publicly available Moroccan Arabic datasets including translation, summarization and sentiment analysis.
• Translated English and multi-lingual instruction-tuning datasets.

Our training dataset Darija-SFT-Mixture is publicly available.

Implementation Information

Atlas-Chat models are based on Gemma 2 models. The Atlas-Chat models were trained using 8 Nvidia's A100 80 GB GPUs in parallel using FSDP on AWS Sagemaker. The model is trained using HuggingFace transformers and parameter-efficient fine-tuning with LoRA rank of 256.

Evaluation

The Atlas-Chat models were evaluated on a comprehensive suite of tasks using various datasets and benchmarks to assess their performance across multiple dimensions. These included tasks such as:

• DarijaMMLU: A Darija version of ArabicMMLU and MMLU benchmarks translated from MSA and English respectively.
• DarijaHellaSwag: A Darija version of HellaSwag.
• Belebele Ary_Arab: Belebele is a multiple-choice machine reading comprehension dataset published by Facebook spanning 122 language variants. The Evaluation is done on the Ary_Arab part of Belebele that refers to Darija.
• Sentiment Analysis.
• Translation: Including six directions and four languages: Darija, MSA, English and French.
• Summarization.

The models were compared against a collection of existing open-source Arabic models to gauge their effectiveness, with a particular focus on performance in Darija. All scores are based on zero-shot performance. The prompts are written mainly in Darija. The metric used for DarijaMMLU, DarijaHellaSwag, Belebele Ary and Sentiment Analysis is the normalized accuracy. We used Language Model Evaluation Harness to conduct these evaluations.

Usage and Limitations

These models have certain limitations that users should be aware of.

Acknowledgement

We would like to express our gratitude to the following institutions for their contributions to this work: École Polytechnique, LINAGORA and KTH Royal Institute of Technology. Additionally, we extend our thanks to the AtlasIA community.