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: 'ai21/jamba-1-5-mini',
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="ai21/jamba-1-5-mini",
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
💡 Discover Jamba 1.5 Mini: AI21 Labs' Latest Hybrid LLM
At a Glance: Jamba 1.5 Mini
- Model Name: Jamba 1.5 Mini
- Developer: AI21 Labs
- Release Date: August 2024
- Version: 1.0
- Model Type: Large Language Model (LLM) utilizing a Hybrid SSM-Transformer architecture
Overview
Jamba 1.5 Mini represents a significant leap in large language model technology. Developed by AI21 Labs and launched in August 2024, this cutting-edge hybrid SSM-Transformer model is engineered for exceptional efficiency and robust performance. It particularly shines in instruction-following tasks and is highly adept at processing extensive context lengths, delivering high-quality outputs across a broad spectrum of natural language processing applications. Its design ensures both speed and accuracy, making it a versatile tool for various digital solutions.
🚀 Accelerated Performance & Advanced Capabilities
Key Features
- ✅ Ultra-Fast Inference: Achieve up to 2.5 times faster inference speeds compared to other leading models, crucial for real-time applications.
- ✅ Superior Long Context Handling: Expertly manages context lengths of up to 256,000 tokens, enabling deep comprehension of complex and lengthy documents.
- 🌍 Extensive Multilingual Support: Offers comprehensive language capabilities across English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew, facilitating global deployment.
- 💰 Business-Oriented Functionality: Includes specialized features like function calling and the generation of structured JSON output, streamlining integration into enterprise workflows.
- 🔧 Optimized Single-GPU Deployment: Utilizes the innovative ExpertsInt8 quantization technique for efficient deployment on a single 80GB GPU, maximizing resource utilization.
Intended Applications
Jamba 1.5 Mini is ideal for diverse applications requiring advanced language processing and efficiency:
- 💬 Intelligent Chatbots and Virtual Assistants
- 📞 Automated Customer Service Solutions
- 📝 Advanced Content Generation and Summarization
- 🔍 Efficient Processing of Extensive Information in various business contexts
🔧 Technical Specifications & Training
Architecture Breakdown
The core of Jamba 1.5 Mini is its innovative hybrid SSM-Transformer architecture. This design synergizes traditional Transformer layers with advanced Mamba layers and an efficient Mixture-of-Experts (MoE) module, delivering optimal performance for sequence modeling and parallel processing.
- ⭐ Active Parameters: 12 billion
- ⭐ Total Parameters: Approximately 52 billion
- ⭐ Context Length Capability: Up to 256K tokens
- ⭐ Attention Heads: Configurable based on specific architectural needs
Training Data & Philosophy
Jamba 1.5 Mini's advanced instruction-following and conversational abilities stem from its training on a rich and varied dataset.
- 📄 Data Source & Scope: Trained on a broad range of texts from multiple domains to ensure robust language understanding.
- 📅 Knowledge Cutoff Date: March 5, 2024
- 🏵 Bias Mitigation & Diversity: The dataset was carefully curated to minimize biases and maximize diversity in topics and languages, contributing to the model's resilience across different real-world contexts.
Performance & Comparative Benchmarks
Jamba 1.5 Mini consistently demonstrates strong competitive performance against other models. Visual benchmarks are provided below:
How Jamba 1.5 Mini Compares
Review the comparative analysis to see where Jamba 1.5 Mini stands among other industry-leading models:
💻 Integrate Jamba 1.5 Mini into Your Workflow
Accessing the API & Code Samples
Jamba 1.5 Mini is conveniently available on the AI/ML API platform. Developers can access it under the model name "Jamba 1.5 Mini".
Here's an example of how to reference the model in your code:
<snippet data-name="open-ai.chat-completion" data-model="ai21/jamba-1-5-mini"></snippet>For more information and to get started, visit the official AI/ML API platform: AI/ML API
Comprehensive API Documentation
For detailed instructions, integration guides, and advanced usage patterns, consult the official API Documentation.
Access the full documentation here: API Documentation
📚 Ethical Framework & Licensing
Commitment to Ethical AI
AI21 Labs places a strong emphasis on ethical AI development. They promote full transparency regarding Jamba 1.5 Mini's capabilities and its inherent limitations. Users are actively encouraged to practice responsible usage to mitigate the risk of misuse or any harmful applications, ensuring the model's positive impact.
Licensing Details
Jamba 1.5 Mini is released under the Jamba Open Model License. This license provides flexible usage rights, permitting both commercial and non-commercial applications, all while ensuring adherence to established ethical standards. This open licensing model aims to foster broad innovation and accessibility.
Ready to harness the power of Jamba 1.5 Mini?
Get Jamba 1.5 Mini API Access Here!❓ Frequently Asked Questions (FAQ)
1. What is Jamba 1.5 Mini?
Jamba 1.5 Mini is a cutting-edge hybrid SSM-Transformer large language model (LLM) developed by AI21 Labs, known for its high efficiency in instruction-following tasks and extensive context processing.
2. What are the main advantages of Jamba 1.5 Mini?
Key advantages include up to 2.5 times faster inference, support for contexts up to 256,000 tokens, multilingual capabilities, and business-focused features like function calling and structured JSON output.
3. Which languages does Jamba 1.5 Mini support?
It supports numerous languages, including English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew.
4. How can developers access and integrate Jamba 1.5 Mini?
Jamba 1.5 Mini is available through the AI/ML API platform. Detailed API documentation and code samples can be found on their official documentation portal.
5. Is commercial use permitted for Jamba 1.5 Mini?
Yes, Jamba 1.5 Mini is released under the Jamba Open Model License, which allows for both commercial and non-commercial usage, adhering to specified ethical guidelines.
Learn how you can transformyour company with AICC APIs
