Athena-1 is a fine-tuned, instruction-following large language model derived from Qwen/Qwen2.5-7B-Instruct. Designed to balance efficiency and performance, Athena 7B provides powerful text-generation capabilities, making it suitable for a variety of real-world applications, including conversational AI, content creation, and structured data processing.

Key Features

🚀 Enhanced Performance

Instruction Following: Fine-tuned for excellent adherence to user prompts and instructions.
Coding and Mathematics: Proficient in solving coding problems and mathematical reasoning.
Lightweight: At 7.62 billion parameters, Athena-1-7B offers powerful performance while maintaining efficiency.

📖 Long-Context Understanding

Context Length: Supports up to 128K tokens, ensuring accurate handling of large documents or conversations.
Token Generation: Can generate up to 8K tokens of output.

🌍 Multilingual Support

Supports 29+ languages, including:
- English, Chinese, French, Spanish, Portuguese, German, Italian, Russian
- Japanese, Korean, Vietnamese, Thai, Arabic, and more.

📊 Structured Data & Outputs

Structured Data Interpretation: Understands and processes structured formats like tables and JSON.
Structured Output Generation: Generates well-formatted outputs, including JSON and other structured formats.

Model Details

Base Model: Qwen/Qwen2.5-7B-Instruct
Architecture: Transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias.
Parameters: 7.62B total (6.53B non-embedding).
Layers: 28
Attention Heads: 28 for Q, 4 for KV.
Context Length: Up to 131,072 tokens.

Applications

Athena-1 is designed for a broad range of use cases:

Conversational AI: Create natural, human-like chatbot experiences.
Code Generation: Generate, debug, or explain code snippets.
Mathematical Problem Solving: Assist with complex calculations and reasoning.
Document Processing: Summarize or analyze large documents.
Multilingual Applications: Support for diverse languages for translation and global use cases.
Structured Data: Process and generate structured data, including tables and JSON.

Quickstart

Here’s how you can use Athena 7B for quick text generation:

python

# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="Spestly/Athena-1-7B")
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Spestly/Athena-1-7B")
model = AutoModelForCausalLM.from_pretrained("Spestly/Athena-1-7B")