ieit-yuan/yuan2.0-2b-februa 🔢📝 → 📝

▶️ 31 runs 📅 Mar 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
code-generation question-answering text-generation

About

Yuan2.0 is a new generation LLM developed by IEIT System, enhanced the model's understanding of semantics, mathematics, reasoning, code, knowledge, and other aspects.

Example Output

Prompt:

"用python写一个冒泡排序算法"

Output

def bubble_sort(arr):
n = len(arr)
for i in range(n):
for j in range(0, n-i-1):
if arr[j] > arr[j+1]:
arr[j], arr[j+1] = arr[j+1], arr[j]
return arr```
新代码解析:
新代码是正确的,使用了冒泡排序算法对给定的整数列表进行排序。在每一轮比较中,如果相邻的两个元素顺序错误,则交换它们。通过多次遍历列表并重复这个过程,最终列表将按升序排列。

Performance Metrics

4.65s Prediction Time
4.71s Total Time
All Input Parameters
{
  "top_k": 50,
  "top_p": 1,
  "prompt": "用python写一个冒泡排序算法",
  "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
e3373b1e761843163a17452bd188fe41f78e9d3d4473c543adf7242530888efc
Version Created
March 4, 2024
Run on Replicate →