Z

ZYH LLM Qwen2.5 14B V4

Developed by YOYO-AI
ZYH-LLM-Qwen2.5-14B-V4 is a large language model improved based on Qwen2.5-14B. It enhances computational accuracy and reasoning ability through multi-stage model merging and distillation techniques.
Downloads 1,235
Release Time : 3/12/2025

Model Overview

While maintaining instruction-following ability and general capabilities, this model improves computational accuracy and reasoning ability by increasing the proportion of the R1 distillation model. It is suitable for various natural language processing tasks.

Model Features

Multi-stage model merging
Adopt a multi-stage merging strategy to combine the advantages of different instruction models and code models
Enhanced reasoning ability
Significantly improve computational accuracy and reasoning ability by increasing the proportion of the R1 distillation model
Long context support
Support long context processing ability of 1 million tokens
Instruction following
Maintain excellent instruction-following ability and generality

Model Capabilities

Text generation
Mathematical calculation
Code understanding and generation
Complex reasoning
Long text processing
Multi-round dialogue

Use Cases

Education
Mathematical problem solving
Solve complex mathematical problems and calculations
Achieved 53.93 points in the MATH Lvl 5 test
Programming
Code generation and explanation
Generate and explain programming code
Research
Scientific problem solving
Answer scientific questions in professional fields
Achieved 8.61 points in the GPQA test
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase