Athena-3-7B Model Card

Athena generated this model card!

Model Overview

Athena-3-7B is a 7.68-billion-parameter causal language model fine-tuned from Qwen2.5-Math-7B. This model is designed to excel in STEM reasoning, mathematics, and natural language processing tasks, offering advanced instruction-following and problem-solving capabilities.

Model Details

Model Developer: Aayan Mishra
Model Type: Causal Language Model
Architecture: Transformer with Rotary Position Embeddings (RoPE), SwiGLU activation, RMSNorm, Attention QKV bias, and tied word embeddings
Parameters: 7.68 billion total (6.93 billion non-embedding)
Layers: 32
Attention Heads: 24 for query and 4 for key-value (Grouped Query Attention)
Vocabulary Size: Approximately 151,646 tokens
Context Length: Supports up to 131,072 tokens
Languages Supported: Over 29 languages, with strong emphasis on English and mathematical expressions
License: MIT

Training Details

Athena-3-7B was fine-tuned using the Unsloth framework on a single NVIDIA A100 GPU. The fine-tuning process spanned approximately 90 minutes over 60 epochs, utilizing a curated dataset focused on instruction-following, problem-solving, and advanced mathematics. This approach enhances the model's capabilities in academic and analytical tasks.

Intended Use

Athena-3-7B is designed for a range of applications, including but not limited to:

STEM Reasoning: Assisting with complex problem-solving and theoretical explanations.
Academic Assistance: Supporting tutoring, step-by-step math solutions, and scientific writing.
General NLP Tasks: Text generation, summarization, and question answering.
Data Analysis: Interpreting and explaining mathematical and statistical data.

While Athena-3-7B is a powerful tool for various applications, it is not intended for real-time, safety-critical systems or for processing sensitive personal information.

How to Use

To utilize Athena-3-7B, ensure that you have the latest version of the transformers library installed:

pip install transformers

Here's an example of how to load the Athena-3-7B model and generate a response:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Spestly/Athena-3-7B"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Explain the concept of entropy in thermodynamics."
messages = [
    {"role": "system", "content": "You are Maverick, an AI assistant designed to be helpful."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Maverick Search usage 🔍

To use this model with Maverick Search, please refer to this repository

Limitations

Users should be aware of the following limitations:

Biases: Athena-3-7B may exhibit biases present in its training data. Users should critically assess outputs, especially in sensitive contexts.
Knowledge Cutoff: The model's knowledge is current up to August 2024. It may not be aware of events or developments occurring after this date.
Language Support: While the model supports multiple languages, performance is strongest in English and technical content.

Acknowledgements

Athena-3-7B builds upon the work of the Qwen team. Gratitude is also extended to the open-source AI community for their contributions to tools and frameworks that facilitated the development of Athena-3-7B.

License

Athena-3-7B is released under the MIT License, permitting wide usage with proper attribution.

Contact

Email: [email protected]

Spestly
/

Athena-3-7B