CalamitousFelicitousness/Qwen2.5-72B-Instruct-fp8-dynamic
CalamitousFelicitousness/Qwen2.5-72B-Instruct-fp8-dynamic is a 72.7 billion parameter instruction-tuned causal language model from the Qwen2.5 series, developed by Qwen. This model significantly enhances coding, mathematics, and instruction following capabilities, building upon the Qwen2 architecture. It features a 131,072 token context length and improved generation of structured outputs like JSON, making it suitable for complex, long-form tasks and multilingual applications.
Loading preview...
Qwen2.5-72B-Instruct Overview
This model is the 72.7 billion parameter instruction-tuned variant of the Qwen2.5 series, developed by Qwen. It represents a significant advancement over Qwen2, particularly in its enhanced knowledge base and specialized capabilities.
Key Capabilities & Improvements
- Enhanced Coding and Mathematics: Incorporates specialized expert models for superior performance in these domains.
- Improved Instruction Following: Demonstrates significant advancements in adhering to complex instructions and generating structured outputs, including JSON.
- Long-Context Support: Features an extensive context window of up to 131,072 tokens for input and can generate texts up to 8,192 tokens, with support for YaRN scaling for even longer texts.
- Multilingual Proficiency: Supports over 29 languages, including major global languages like Chinese, English, French, Spanish, and Japanese.
- Robustness: More resilient to diverse system prompts, improving role-play and chatbot condition-setting.
Architecture and Features
Built on a transformer architecture, Qwen2.5-72B-Instruct utilizes RoPE, SwiGLU, RMSNorm, and Attention QKV bias. It is designed for both pretraining and post-training stages, offering a powerful foundation for various NLP tasks. For detailed evaluation and performance metrics, refer to the official blog.