API
If you're looking for an API, you can choose from your desired programming language.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
const axios = require('axios');
const api_key = "YOUR API-KEY";
const url = "https://api.segmind.com/v1/mixtral-8x7b-instruct";
const data = {
"messages": [
{
"role": "user",
"content": "tell me a joke on cats"
},
{
"role": "assistant",
"content": "here is a joke about cats..."
},
{
"role": "user",
"content": "now a joke on dogs"
}
]
};
(async function() {
try {
const response = await axios.post(url, data, { headers: { 'x-api-key': api_key } });
console.log(response.data);
} catch (error) {
console.error('Error:', error.response.data);
}
})();Attributes
An array of objects containing the role and content
Could be "user", "assistant" or "system".
A string containing the user's query or the assistant's response.
To keep track of your credit usage, you can inspect the response headers of each API call. The x-remaining-credits property will indicate the number of remaining credits in your account. Ensure you monitor this value to avoid any disruptions in your API usage.
Mixtral 8x7b
Mixtral 8x7b is a large language model (LLM) created by Mistral AI. It's known for being efficient and powerful. Here's a quick rundown of its key features:
-
Efficient: Mixtral 8x7b is a sparse model, meaning it only uses a portion of its parameters at a time. This makes it faster and cheaper to run than some other LLMs.
-
Powerful: Despite its efficiency, Mixtral 8x7b performs well on many benchmarks, even exceeding some larger models.
-
Multilingual: It can understand and respond in English, French, Italian, German, and Spanish.
-
Open-source: The code is available for anyone to use and modify.
Other Popular Models
sdxl-controlnet
SDXL ControlNet gives unprecedented control over text-to-image generation. SDXL ControlNet models Introduces the concept of conditioning inputs, which provide additional information to guide the image generation process
faceswap-v2
Take a picture/gif and replace the face in it with a face of your choice. You only need one image of the desired face. No dataset, no training
sdxl-inpaint
This model is capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask
sd1.5-majicmix
The most versatile photorealistic model that blends various models to achieve the amazing realistic images.
