Code Llama is a collection of pretrained and fine-tuned Large Language Models ranging in scale from 7 billion to 70 billion parameters, specializing in using both code and natural language prompts to generate code and natural language about code. This is the 70B Python specialist version.
import requests
import json
url = "https://api.cyfuture.ai/aiapi/inferencing/response"
payload = {
"model": "Model Name",
"max_tokens": 16384,
"top_p": 1,
"top_k": 40,
"presence_penalty": 0,
"frequency_penalty": 0,
"temperature": 0.6,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}
headers = {
"Accept": "application/json",
"Content-Type": "application/json",
"Authorization": "Bearer <API_KEY>"
}
requests.request("POST", url, headers=headers, data=json.dumps(payload))await fetch("https://api.cyfuture.ai/aiapi/inferencing/response", {
method: "POST",
headers: {
"Accept": "application/json",
"Content-Type": "application/json",
"Authorization": "Bearer <API_KEY>"
},
body: JSON.stringify({
model: ""Model Name"",
max_tokens: 16384,
top_p: 1,
top_k: 40,
presence_penalty: 0,
frequency_penalty: 0,
temperature: 0.6,
messages: [
{
role: "user",
content: "Hello, how are you?"
}
]
})
});URI uri = URI.create("https://api.cyfuture.ai/aiapi/inferencing/response");
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(uri)
.header("Accept", "application/json")
.header("Content-Type", "application/json")
.header("Authorization", "Bearer <API_KEY>")
.POST(HttpRequest.BodyPublishers.ofString("""{
"model": ""Model Name"",
"max_tokens": 16384,
"top_p": 1,
"top_k": 40,
"presence_penalty": 0,
"frequency_penalty": 0,
"temperature": 0.6,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}"""))
.build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
package main
import (
"bytes"
"net/http"
"fmt"
)
apiUrl := "https://api.cyfuture.ai/aiapi/inferencing/response"
var jsonData = []byte(`{
"model": "Model Name",
"max_tokens": 16384,
"top_p": 1,
"top_k": 40,
"presence_penalty": 0,
"frequency_penalty": 0,
"temperature": 0.6,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}`)
req, err := http.NewRequest(POST, apiUrl, bytes.NewBuffer(jsonData))
req.Header.Set("Accept", "application/json")
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Authorization", "Bearer <API_KEY>")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
fmt.Println("response Status:", resp.Status)curl --request POST \
--url https://api.cyfuture.ai/aiapi/inferencing/response \
-H 'Accept: application/json' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer <API_KEY>' \
--data '{
"model": "Model Name",
"max_tokens": 16384,
"top_p": 1,
"top_k": 40,
"presence_penalty": 0,
"frequency_penalty": 0,
"temperature": 0.6,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}'On-demand deployments allow you to use Code Llama 70B Python on dedicated GPUs with Cyfuture AI' high-performance serving stack with high reliability and no rate limits.
See the On-demand deployments guide for details.
