趋近智
GreenMind-14B-R1
参数
14B
上下文长度
32.768K
模态
Text
架构
Dense
许可证
Apache-2.0
发布日期
23 Sept 2024
训练数据截止日期
-
技术规格
注意力结构
Multi-Head Attention
隐藏维度大小
-
层数
-
注意力头
-
键值头
-
激活函数
-
归一化
-
位置嵌入
Absolute Position Embedding
系统要求
不同量化方法和上下文大小的显存要求
GreenMind-14B-R1
GreenMind-14B-R1 is a 14 billion parameter reasoning model optimized for Vietnamese. It utilizes a self-improving data feedback loop to perform multi-step reasoning in logic and mathematics. The model is specifically optimized for NVIDIA NIM deployment and is designed for Vietnamese-focused AI assistants.
关于 GreenMind
GreenMind is an open-source Vietnamese reasoning language model family developed by GreenNode. It is optimized for multi-step reasoning tasks in Vietnamese, such as logic, mathematics, and scenario analysis. The model is designed to run efficiently on single-GPU hardware configurations.
其他 GreenMind 模型
- 没有相关模型
评估基准
没有可用的 GreenMind-14B-R1 评估基准。