OpenAI - ChatGPT, Sora
Google - Gemini, Nano Banana
Anthropic - Claude
xAI - Grok
Deepseek
Alibaba - Qwen
ByteDance - Doubao
All Models
Enterprise Plans
AI Application Development
AI Translator API
AI SEO/GEO Service
GEO-Optimized PR Service
Web Scraping Service
Top AI Tools
Top AI Robots
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: 'togethercomputer/guanaco-13b',
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="togethercomputer/guanaco-13b",
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}")
Product Detail
Discover Guanaco-13B, an advanced open-source, fine-tuned large language model (LLM) engineered to excel in creating high-quality, multilingual chatbots. Built upon the robust LLaMA base model, Guanaco-13B offers performance comparable to leading commercial systems like ChatGPT and BARD, making it an invaluable tool for researchers and developers.
✨ Key Features of Guanaco-13B
- Open-source Nature: Freely available for research and experimentation.
- Efficient Fine-tuning: Utilizes 4-bit QLoRA fine-tuning on the extensive OASST1 dataset.
- Model Versatility: Available in multiple sizes (7B, 13B, 33B, 65B parameters), catering to various computational needs. This particular version is 13B.
- Multilingual Support: Optimized for high-resource languages, facilitating global chatbot development.
- Competitive Performance: Delivers results on par with commercial giants in the LLM space.
🚀 Intended Use Cases
Guanaco-13B is specifically designed for AI researchers and developers. It empowers them to conduct cost-effective and local experiments with cutting-edge, high-quality multilingual chatbot systems. Its open-source nature fosters innovation and collaboration within the AI community.
💡 Technical Specifications
Architecture Overview
The Guanaco-13B model is architecturally rooted in the LLaMA base model. It enhances its capabilities through the integration of LoRA (Low-Rank Adaptation) adapters across all layers, with a rank of 64, optimizing its performance and efficiency.
Training Data & Fine-tuning
The model undergoes fine-tuning on the OASST1 (Open Assistant Supervised Task 1) dataset. This dataset, while multilingual, has a significant emphasis on high-resource languages. Composed of human-written conversations, OASST1 is crucial for enabling Guanaco-13B to learn and generate natural, engaging dialogue patterns. The exact size of the dataset used for fine-tuning this specific version has not been publicly detailed.
Knowledge Cutoff & Biases
The specific knowledge cutoff date for Guanaco-13B is not explicitly provided in the available documentation. Due to its training on a multilingual dataset like OASST1, Guanaco-13B has the potential to exhibit reduced bias compared to models trained on monolingual data. However, the dataset's inherent focus on high-resource languages might still introduce some language-specific biases.
Performance Benchmarking
Guanaco-13B has demonstrated competitive performance metrics, matching commercial systems such as ChatGPT and BARD on recognized benchmarks like Vicuna and OpenAssistant.
🛠️ Usage & Guidelines
API Usage Example
// Example using a hypothetical API endpoint import requests url = "https://api.example.com/v1/chat/completions" headers = { "Content-Type": "application/json", "Authorization": "Bearer YOUR_API_KEY" } data = { "model": "togethercomputer/guanaco-13b", "messages": [ {"role": "user", "content": "Tell me a fun fact about giraffes."} ] } response = requests.post(url, headers=headers, json=data) print(response.json())Ethical Considerations & Licensing
While specific ethical guidelines for Guanaco-13B's use have not been publicly released by its developers, users are strongly encouraged to adhere to general ethical AI principles. The model is released under an open-source license, primarily for research and non-commercial purposes, though the precise license type is not detailed in the documentation. Users should verify the current licensing terms for any specific deployment.
❓ Frequently Asked Questions (FAQ)
Q: What is Guanaco-13B?
A: Guanaco-13B is an open-source, fine-tuned large language model (LLM) based on the LLaMA architecture, designed for creating high-quality, multilingual chatbots.
Q: Is Guanaco-13B free to use?
A: Yes, it is released under an open-source license, primarily for research and non-commercial experimentation. Specific commercial use might require checking the detailed license terms.
Q: What datasets were used to train Guanaco-13B?
A: Guanaco-13B was fine-tuned using the OASST1 (Open Assistant Supervised Task 1) dataset, which consists of human-written conversations and is multilingual.
Q: How does Guanaco-13B compare to commercial models like ChatGPT?
A: Guanaco-13B has demonstrated competitive performance with commercial systems like ChatGPT and BARD on various benchmarks, offering a strong open-source alternative.
Q: Can Guanaco-13B support multiple languages?
A: Yes, it offers multilingual support, with a focus on high-resource languages, enabled by its fine-tuning on the OASST1 dataset.
AI Playground
