Update README.md

README.md

@@ -17,6 +17,157 @@ language:
 This model was converted to GGUF format from [`Spestly/Athena-1-0.5B`](https://huggingface.co/Spestly/Athena-1-0.5B) 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-1-0.5B) for more details on the model.
 
+---
+Model details:
+-
+Athena-1 0.5B is a fine-tuned, instruction-following large language model derived from Qwen/Qwen2.5-0.5B-Instruct.
+ Designed for ultra-lightweight applications, Athena-1 0.5B balances 
+compactness with robust performance, making it suitable for tasks with 
+limited computational resources.
+
+
+
+
+	
+		
+	
+
+		Key Features
+	
+
+
+
+
+	
+		
+	
+
+		⚡ Ultra-Lightweight and Efficient
+	
+
+
+
+Compact Size: With just 500 million parameters, Athena-1 0.5B is ideal for edge devices and low-resource environments.
+Instruction Following: Fine-tuned for reliable adherence to user instructions.
+Coding and Mathematics: Capable of handling basic coding and mathematical tasks.
+
+
+
+	
+		
+	
+
+		📖 Contextual Understanding
+	
+
+
+
+Context Length: Supports up to 16,384 tokens, enabling processing of moderately sized conversations or documents.
+Token Generation: Can generate up to 4K tokens of coherent output.
+
+
+
+	
+		
+	
+
+		🌍 Multilingual Support
+	
+
+
+
+Supports 20+ languages, including:
+English, Chinese, French, Spanish, German, Italian, Russian
+Japanese, Korean, Vietnamese, Thai, and more.
+
+
+
+
+
+	
+		
+	
+
+		📊 Structured Data & Outputs
+	
+
+
+
+Structured Data Interpretation: Handles formats like tables and JSON effectively.
+Structured Output Generation: Produces well-formatted outputs for data-specific tasks.
+
+
+
+
+	
+		
+	
+
+		Model Details
+	
+
+
+
+Base Model: Qwen/Qwen2.5-0.5B-Instruct
+Architecture: Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings.
+Parameters: 500M total.
+Layers: (Adjust if different from the base model)
+Attention Heads: (Adjust if different from the base model)
+Context Length: Up to 16,384 tokens.
+
+
+
+
+	
+		
+	
+
+		Applications
+	
+
+
+
+Athena-1 0.5B is optimized for:
+
+
+Conversational AI: Power lightweight and responsive chatbots.
+Code Assistance: Basic code generation, debugging, and explanations.
+Mathematical Assistance: Solves fundamental math problems.
+Document Processing: Summarizes and analyzes smaller documents effectively.
+Multilingual Tasks: Supports global use cases with a compact model.
+Structured Data: Reads and generates structured formats like JSON and tables.
+
+
+
+
+	
+		
+	
+
+		Quickstart
+	
+
+
+
+Here’s how you can use Athena-1 0.5B for quick text generation:
+
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+messages = [
+    {"role": "user", "content": "What can you do?"},
+]
+pipe = pipeline("text-generation", model="Spestly/Athena-1-0.5B") # Update model name
+print(pipe(messages))
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("Spestly/Athena-1-0.5B") # Update model name
+model = AutoModelForCausalLM.from_pretrained("Spestly/Athena-1-0.5B") # Update model name
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)