Llama-3.1-8B-FINLLM

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

from transformers import BitsAndBytesConfig, AutoModelForCausalLM, AutoTokenizer
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, pipeline
import logging
# Suppress all warnings
logging.getLogger("transformers").setLevel(logging.CRITICAL) #weird warning when using model for inference

# Check if CUDA is available
if torch.cuda.is_available():
    num_devices = torch.cuda.device_count()
    print(f"Number of available CUDA devices: {num_devices}")
    
    for i in range(num_devices):
        device_name = torch.cuda.get_device_name(i)
        print(f"\nDevice {i}: {device_name}")
else:
    print("CUDA is not available.")
# Specify the device (0 for GPU or -1 for CPU)
device = 0 if torch.cuda.is_available() else -1

config = PeftConfig.from_pretrained("smartinez1/Llama-3.1-8B-FINLLM")
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B")
model = PeftModel.from_pretrained(base_model, "smartinez1/Llama-3.1-8B-FINLLM")
# Load the tokenizer associated with the base model
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B")
# Define the unique padding token for fine-tuning
custom_pad_token = "<|finetune_right_pad_id|>"
tokenizer.add_special_tokens({'pad_token': custom_pad_token})
pad_token_id = tokenizer.pad_token_id

# Set up the text generation pipeline with the PEFT model, specifying the device
generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)

# List of user inputs
user_inputs = [
    "Provide a link for Regulation A (Extensions of Credit by Federal Reserve Banks) law",
    "Define the following term: Insurance Scores.",
    "Expand the following acronym into its full form: ESCB.",
    "Provide a concise answer to the following question: Which countries currently have bilateral FTAs in effect with the U.S.?",
    """Given the following text, only list the following for each: specific Organizations, Legislations, Dates, Monetary Values, 
    and Statistics When can counterparties start notifying the national competent authorities (NCAs) of their intention to apply 
    the reporting exemption in accordance with Article 9(1) EMIR, as amended by Regulation 2019/834?""",
    "Provide a concise answer to the following question: What type of license is the Apache License, Version 2.0?"
]

# Define the prompt template
prompt_template = """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{}

### Answer:
"""

# Loop over each user input and generate a response
for user_input in user_inputs:
    # Format the user input into the prompt
    prompt = prompt_template.format(user_input)

    # Generate a response from the model
    response = generator(prompt, max_length=200, num_return_sequences=1, do_sample=True)

    # Extract and clean up the AI's response
    response_str = response[0]['generated_text'].split('### Answer:')[1].strip()
    cut_ind = response_str.find("#")  # Remove extra information after the response
    response_str = response_str[:cut_ind].strip() if cut_ind != -1 else response_str

    # Display the AI's response
    print(f"User: {user_input}")
    print(f"AI: {response_str}")
    print("-" * 50)  # Separator for clarity

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

• PEFT 0.13.2