Enterprise Plans
AI Application Development
AI Translator API
AI SEO/GEO Service
Web Scraping Service
Log in
const { OpenAI } = require('openai');
const api = new OpenAI({
baseURL: 'https://api.ai.cc/v1',
apiKey: '',
});
const main = async () => {
const result = await api.chat.completions.create({
model: 'zero-one-ai/Yi-34B-Chat',
messages: [
{
role: 'system',
content: 'You are an AI assistant who knows everything.',
},
{
role: 'user',
content: 'Tell me, why is the sky blue?'
}
],
});
const message = result.choices[0].message.content;
console.log(`Assistant: ${message}`);
};
main();
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.ai.cc/v1",
api_key="",
)
response = client.chat.completions.create(
model="zero-one-ai/Yi-34B-Chat",
messages=[
{
"role": "system",
"content": "You are an AI assistant who knows everything.",
},
{
"role": "user",
"content": "Tell me, why is the sky blue?"
},
],
)
message = response.choices[0].message.content
print(f"Assistant: {message}")
-
AI Playground
Test all API models in the sandbox environment before you integrate.
We provide more than 300 models to integrate into your app.
Product Detail
✨ Elevate Your AI Solutions with Yi Series LLMs
The Yi series models represent a new benchmark in Large Language Models (LLMs), recognized globally for their exceptional performance. Architected as truly bilingual models, they have been rigorously trained on an expansive 3-terabyte multilingual corpus. This extensive training empowers the Yi series with unparalleled capabilities in:
- • Language Comprehension: Deep understanding across diverse linguistic contexts.
- • Commonsense Reasoning: Robust ability to infer and understand everyday knowledge.
- • Reading Comprehension: Superior capacity to extract and interpret information from text.
Discover the full potential of these advanced LLMs firsthand. We invite you to try out the Yi series at our dedicated AI API Playground.
💡 Key Use Cases for the Yi-34B Model
The Yi-34B model is specifically engineered for robust performance in interactive and conversational AI. Its fine-tuned capabilities make it an excellent fit for diverse applications across various sectors:
-
💬
Customer Service Chatbots: Enhancing user experience with intelligent, responsive customer support systems.
-
⚙️
Technical Support Automation: Providing efficient, accurate solutions to technical queries.
-
📚
Educational Tutoring: Offering personalized learning assistance and academic guidance.
-
✍️
Creative Writing Support: Aiding content creators in generating ideas, drafting, and refining written works.
🔍 Yi-34B in the LLM Landscape: Mixtral and ChatGPT
While direct, comprehensive benchmark comparisons between Yi-34B and other prominent models like Mixtral or ChatGPT are not provided in this overview, it's important to understand Yi-34B's strategic positioning.
As outlined, Yi-34B is primarily optimized and utilized for customer service chatbots and interactive applications, including specialized roles in technical support, educational tutoring, and creative writing. Its strengths lie in its fine-tuned capabilities for these specific, high-engagement scenarios, particularly leveraging its bilingual proficiency. For organizations seeking a focused, robust, and multilingual solution for these use cases, Yi-34B offers a compelling and effective choice.
⚙️ Optimizing Yi-34B: Best Practices and Tips
To fine-tune the Yi-34B model's output and ensure it meets your specific requirements, consider implementing the following expert tips:
-
🌡️
Temperature Setting: Yi-34B can generate highly creative (or "hot") outputs by default. We recommend adjusting the temperature to approximately 0.5 for a balance between creativity and consistency.
-
🔁
Repetition Penalty: To prevent the model from generating repetitive phrases or sentences, set the repetition penalty between 1.1 and 1.2.
-
🎯
Minimum Probability (min_p): To avoid overly generic or uncreative one-sentence responses, configure min_p between 0.05 and 0.1.
-
📝
Instruction Template: The model consistently performs well when utilizing the "ChatML" instruction template for prompts.
-
🛑
Custom Stopping String: If you notice the model frequently outputs
<s>at the end of its answers, use<s>as a custom stopping string to ensure cleaner outputs. -
➡️
Beginning of Sentence (BOS) Token: For certain Yi models, performance can be enhanced by unchecking the "Add the bos_token to the beginning of prompts" option.
💻 API Integration Example
Integrating Yi-34B into your application is straightforward. Here's a typical API snippet for a chat completion:
<snippet data-name="open-ai.chat-completion" data-model="zero-one-ai/Yi-34B-Chat"></snippet>
Refer to our comprehensive API documentation for more detailed examples, authentication procedures, and advanced configurations.
❓ Frequently Asked Questions (FAQ)
The Yi series models are distinguished by their bilingual design and training on a massive 3T multilingual corpus, leading to superior performance in language comprehension, commonsense reasoning, and reading comprehension.
Yi-34B is primarily utilized for customer service chatbots and interactions, technical support, educational tutoring, and creative writing assistance across various industries.
To optimize responses, consider adjusting the Temperature to around 0.5, setting the Repetition Penalty between 1.1-1.2, and Min_p between 0.05-0.1. Using the "ChatML" instruction template is also highly effective.
Absolutely. Designed as a bilingual model and trained on a 3T multilingual corpus, Yi-34B is highly capable of understanding and generating content in multiple languages, making it ideal for diverse linguistic applications.
You can easily try out the Yi series models and experiment with their capabilities at our dedicated AI API Playground.
Learn how you can transformyour company with AICC APIs
