Update README.md

README.md

@@ -17,6 +17,159 @@ language:
 This model was converted to GGUF format from [`Spestly/Athena-1-3B`](https://huggingface.co/Spestly/Athena-1-3B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/Spestly/Athena-1-3B) for more details on the model.
 
+---
+Model details:
+-
+Athena-1 3B is a fine-tuned, instruction-following large language model derived from Qwen/Qwen2.5-3B-Instruct.
+ It is designed to provide efficient, high-quality text generation while
+ maintaining a compact size. Athena 3B is optimized for lightweight 
+applications, conversational AI, and structured data tasks, making it 
+ideal for real-world use cases where performance and resource efficiency
+ are critical.
+
+
+
+
+	
+		
+	
+
+		Key Features
+	
+
+
+
+
+	
+		
+	
+
+		⚡ Lightweight and Efficient
+	
+
+
+
+Compact Size: At just 3.09 billion parameters, Athena-1 3B offers excellent performance with reduced computational requirements.
+Instruction Following: Fine-tuned for precise and reliable adherence to user prompts.
+Coding and Mathematics: Proficient in solving coding challenges and handling mathematical tasks.
+
+
+
+	
+		
+	
+
+		📖 Long-Context Understanding
+	
+
+
+
+Context Length: Supports up to 32,768 tokens, enabling the processing of moderately lengthy 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: 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/Qwen2.5-3B-Instruct
+Architecture: Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings.
+Parameters: 3.09B total (2.77B non-embedding).
+Layers: 36
+Attention Heads: 16 for Q, 2 for KV.
+Context Length: Up to 32,768 tokens.
+
+
+
+
+	
+		
+	
+
+		Applications
+	
+
+
+
+Athena 3B is designed for a variety of real-world applications:
+
+
+Conversational AI: Build fast, responsive, and lightweight chatbots.
+Code Generation: Generate, debug, or explain code snippets.
+Mathematical Problem Solving: Assist with calculations and reasoning.
+Document Processing: Summarize and analyze moderately large documents.
+Multilingual Applications: Support for global use cases with diverse language requirements.
+Structured Data: Process and generate structured data, such as tables and JSON.
+
+
+
+
+	
+		
+	
+
+		Quickstart
+	
+
+
+
+Here’s how you can use Athena 3B for quick text generation:
+
+
+# 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-1-3B")
+pipe(messages)
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("Spestly/Athena-1-3B")
+model = AutoModelForCausalLM.from_pretrained("Spestly/Athena-1-3B")
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)