WizardLM
LLM fine-tuned with Evol-Instruct for complex instruction following.
About
WizardLM by Microsoft Research is a family of instruction-following models trained with Evol-Instruct, a method that automatically rewrites simple instructions into more complex and varied ones to build richer training data. The approach extends to WizardCoder for programming and WizardMath for math reasoning, with models based on Llama 2 in 7B, 13B, and 70B sizes. The work was published at ICLR 2024.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Lightweight open-weight LLM by Google available in 1B to 27B sizes.
Open-source code LLM family by IBM for enterprise code generation.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.
High-performance open-weight MoE LLM with 671B total parameters.
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
Open-weight code LLM trained on 2 trillion tokens of code and natural language.