summarization classification translation NLP media and journalism domain specific llm

Llama2-13B-AIVision360

NewsConnect 13B (Llama2-13B-AIVision360) is a state-of-the-art, open-source chat model that stands as a beacon for technology, media, and AI news discussions. Built on the robust Llama2-13B architecture, this model has been enhanced and refined utilizing the AIVision360-8k dataset, making it a pioneer in the domain of AI news generation and interpretation.

Model Details

Dataset Utilized: AIVision360-8k

Drawing strength from the AIVision360-8k dataset, a curated collection hailing from "ainewshub.ie", this model is tailor-made for technology media and journalism. Offering structured interactions related to AI news, it captures the essence of the latest AI trends and evolutions. For a deeper dive into the dataset visit: AIVision360-8k

Model Specification

Key Features and Functionalities

Domain Specialization

The Llama2-13B-AIVision360 model is specialized in AI news, serving as a resource for AI researchers, enthusiasts, and media experts.

Model API Accessibility

Offers a straightforward Python integration for generating AI news insights.

Performance Optimisation

Efficient performance across both CPU and GPU platforms.

Data Representation

Utilises a comprehensive AI news dataset, enabling content generation akin to professional journalism standards.

Model Usage

Experience the capabilities of the Llama2-13B-AIVision360 model through a well-structured Python interface. To kick-start your exploration, follow the steps and snippets given below:

Prerequisites

1. Ensure required packages are available

import torch
import transformers
from typing import Any, Dict
from transformers import PreTrainedTokenizerFast, AutoTokenizer, 
AutoModelForCausalLM
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    HfArgumentParser,
    TrainingArguments,
    pipeline,
    logging,
)
import time

2. Initiate the model and tokenizer

model_name = "ceadar-ie/Llama2-13B-AIVision360"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", 
torch_dtype=torch.float16, trust_remote_code=True)

3. Create a function for generating text

def generate_text(input_text):
    num_words_input = len(input_text.split())

    start_time = time.time()
    
    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=500,temperature=1, top_k=10, top_p=0.1, repetition_penalty = 1.15)
    prompt = f" [INST] {input_text} [/INST]"
    result = pipe(prompt)
    generated_text = result[0]['generated_text'].replace(prompt, "").strip()

    end_time = time.time()
    time_taken = end_time - start_time

    num_words_generated = len(generated_text.split())

    print("Generated Output:")
    print(generated_text)
    print('=' * 60 )
    print("\nNumber of Words in Input Text:", num_words_input)
    print("Number of Words in Generated Output:", num_words_generated)
    print("Time Taken to Generate Output: {:.2f} seconds".format(time_taken))

Example Evaluation and Use

Example Prompt 1:

List new regulations or guidelines that have been introduced globally concerning AI ethics and bias mitigation.

Generated Output:

Globally, there is a growing concern about the potential negative impacts of artificial intelligence (AI) on society, particularly with regards to ethics and bias. In response, regulators and policymakers have been introducing new guidelines and regulations to address these issues. Some examples of the new regulations and guidelines introduced globally concerning AI ethics and bias mitigation include:

These new regulations and guidelines demonstrate a growing trend towards the regulation of AI and the importance of addressing ethical and bias issues in the development and use of AI technology.

Example Prompt 2:

List What are the current market trends in the AI industry?

Generated Output:

The text provides an overview of the current state of the AI industry, including the performance of various companies and technologies in the sector. The trends listed include the success of Nvidia's H100 GPU, the growing demand for AI chips, and the competition among major tech companies to dominate the AI market. These trends highlight the rapid growth and increasing importance of the AI industry, with a focus on the competitive landscape and the demand for high-performance computing resources. The current market trends in the AI industry include Nvidia's dominance of the H100 GPU, the growing demand for AI chips, and the competition among major tech companies such as Intel, Google, and Microsoft to dominate the AI market. 85% of H100 GPUs sold since January have been used for AI tasks, there is a shortage of AI chips, and the market for programmable AI chips is expected to reach $30 billion by 2025. Additionally, major tech companies are investing heavily in AI research and development, and the market for AI chips is becoming increasingly competitive.

Example Prompt 3:

Concisely list in separate points, any recent controversies or debates in the AI community.

Generated Output:

Recent controversies and debates in the AI community include:

Example Prompt 4:

Concisely list in separate points, sectors or industries that are seeing the most rapid AI adoption right now. Do not repeat provided information.

Generated Output:

Sectors and industries are rapidly incorporating AI into their processes to improve efficiency and decision-making, according to a report by Forrester Research. The report highlights the urgent need for organizations to adopt AI to remain competitive and agile in the face of changing market conditions and customer demands. Here are the details about the report and its findings:

Here are the sectors or industries that are seeing the most rapid AI adoption right now, based on the report by Forrester Research:

  1. Finance
  2. Healthcare
  3. Retail
  4. Manufacturing

Training Details

Training Hyperparameters

Model Limitations

Potential Biases: With its fine-tuning centered on AI news sources, inherent biases from these sources may reflect in the model's outputs.

Licensing

The Llama2-13B-AIVision360 model, developed in collaboration with CeADAR Connect Group, combines the licensing frameworks of both Llama2 and AIVision360. Under Meta's terms, users are granted a non-exclusive, worldwide, non-transferable, royalty-free limited license for the use and modification of Llama Materials, inclusive of the Llama2 model and its associated documentation. When redistributing, the provided Agreement and a specific attribution notice must be included. In alignment with the AIVision360 dataset's licensing, the model is also distributed under the Apache 2.0 open-source license, promoting its use and modification within the AI community, while ensuring content reliability sourced from established AI news publishers.

Out-of-Scope Use

Llama2-13B-AIVision360 is specifically tailored for AI news discussions. It is not optimized for:

Bias, Risks, and Limitations

Citation:

@misc {ceadar_2023,
	author       = { {CeADAR} },
	title        = { Llama2-13B-AIVision360 (Revision caa5124) },
	year         = 2023,
	url          = { https://huggingface.co/ceadar-ie/Llama2-13B-AIVision360 },
	doi          = { 10.57967/hf/1124 },
	publisher    = { Hugging Face }
}

Contact:

For any further inquiries or feedback concerning Llama2-13B-AIVision360, please forward your communications to ahtsham.zafar@ucd.ie