---
license: other
tags:
- yi
- moe
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
model-index:
- name: 60B_MoE_Coder_v3
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 71.16
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/60B_MoE_Coder_v3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 85.44
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/60B_MoE_Coder_v3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 75.37
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/60B_MoE_Coder_v3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 67.01
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/60B_MoE_Coder_v3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 82.56
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/60B_MoE_Coder_v3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 66.94
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/60B_MoE_Coder_v3
      name: Open LLM Leaderboard
---
This is an English and Chinese chat model for Coding but also general purpose.

example output


写一个python程序抓取youtube最流行的内容：从网页获取数据，

以下是一个python脚本，可以从Youtube上抓取最受欢迎的视频并将其保存到本地文件中。该脚本使用Selenium WebDriver来模拟浏览器操作以登录并搜索视频，然后利用Beautiful Soup库提取所需信息。如果您需要任何帮助或修改建议，请随时告诉我！

```
from selenium import webdriver
from bs4 import BeautifulSoup as BS
import os

# 设置ChromeDriver路径
CHROMEDRIVER_PATH = './chromedriver.exe' # 更换为实际路径

def main():
    # 启动Chrome浏览器并登录Youtube
    browser = webdriver.Chrome(executable_path=CHROMEDRIVER_PATH)
    browser.get('https://www.youtube.com/')
    login_url = 'https://accounts.google.com/signin'
    browser.get(login_url)
    # 模拟输入账号和密码并登录
    username = input('Username: ')
    password = getpass.getpass() # 防止密码显示在终端上
    submit_button = browser.find_element_by_class_name('whsLW', timeout=5)
    submit_button.click()

    # 在搜索栏中输入关键词并查找结果
    search_query = 'most popular youtube videos today'
    search_box = browser.find_element_by_id('search_query')
    search_box.send_keys(search_query)
    enter_key = browser.find_element_by_class_name('ytp-suggest-renderer__input-icon')
    enter_key.click()
    results = BS(browser.page_source, 'html.parser')

    # 从搜索结果中提取出最受欢迎的视频链接并保存到本地文件
    videos = results.find('ol', {'class': 'r'})
    video_urls = [a['href'] for a in videos.find_all('a')]
    saved_path = 'popular_videos/' + os.getcwd().split('/')[-2] + '_' + str(int(time.time())) + '/'
    if not os.path.exists(saved_path):
        os.makedirs(saved_path)
    for i, url in enumerate(video_urls[:50]):
        filename = saved_path + '%d.mp4' % (i+1)
        urllib.request.urlretrieve(url, filename)
    print('Downloaded top 50 videos to:', saved_path)

except Exception as e:
    print(e)

```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cloudyu__60B_MoE_Coder_v3)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |74.75|
|AI2 Reasoning Challenge (25-Shot)|71.16|
|HellaSwag (10-Shot)              |85.44|
|MMLU (5-Shot)                    |75.37|
|TruthfulQA (0-shot)              |67.01|
|Winogrande (5-shot)              |82.56|
|GSM8k (5-shot)                   |66.94|