ieit-yuan/yuan2.0-2b-mars 🔢📝 → 📝

▶️ 19 runs 📅 Apr 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
code-generation question-answering text-generation translation

About

yuan2.0-2b-mars是源2.0-2B模型的2024年3月版本,源2.0 是浪潮信息发布的新一代基础语言大模型。我们开源了全部的3个模型源2.0-102B,源2.0-51B和源2.0-2B。并且我们提供了预训练,微调,推理服务的相关脚本,以供研发人员做进一步的开发。源2.0是在源1.0的基础上,利用更多样的高质量预训练数据和指令微调数据集,令模型在语义、数学、推理、代码、知识等不同方面具备更强的理解能力。

Example Output

Prompt:

"请问目前最先进的机器学习算法有哪些?"

Output

目前最先进的机器学习算法包括:卷积神经网络(Convolutional Neural Network,CNN)、循环神经网络(Recurrent Neural Network,RNN)、长短时记忆网络(Long Short-Term Memory,LSTM)、生成对抗网络(Generative Adversarial Networks,GAN)和强化学习(Reinforcement Learning,RL)等。这些算法在不同的任务和应用场景中都取得了优异的表现,被广泛应用于计算机视觉、自然语言处理、语音识别、推荐系统等领域。

Performance Metrics

6.42s Prediction Time
6.44s Total Time
All Input Parameters
{
  "top_k": 50,
  "top_p": 1,
  "prompt": "请问目前最先进的机器学习算法有哪些?",
  "temperature": 1,
  "max_new_tokens": 4096
}
Input Parameters
top_k Type: integerDefault: 50
The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
top_p Type: numberDefault: 1
A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string
temperature Type: numberDefault: 1
The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 4096
The maximum number of tokens the model should generate as output.
Output Schema

Output

Type: string

Version Details
Version ID
fc193b6a37ab65602586d0f6979971ecee3c79cc0d8ebf95ed5a93d1f68a440a
Version Created
April 23, 2024
Run on Replicate →