Update README.md

README.md

@@ -17,6 +17,158 @@ language:
 This model was converted to GGUF format from [`Spestly/Athena-1-7B`](https://huggingface.co/Spestly/Athena-1-7B) 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-1-7B) for more details on the model.
 
+---
+Model details:
+-
+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:
+
+
+# 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")
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)