Examples

Sentiment Analysis

You can use togethercomputer/RedPajama-INCITE-7B-Base for classification tasks with longer context. In this guide, you will use the model to classify the sentiment of any sentence as either positive, negative, mixed, or neutral.

Begin the prompt with an instruction describing the task.

Label the sentences as either "positive", "negative", "mixed", or "neutral":

After the instruction, provide a few examples with known labels.

Sentence: I can say that there isn't anything I would change.
Label: positive

Sentence: I'm not sure about this.
Label: neutral

Sentence: I liked some parts but I didn't like other parts.
Label: mixed

Sentence: I think the background image could have been better.
Label: negative

Finally, append the tweet that the model should classify and prompt the model to complete the label.

Sentence: I really like it.
Label:

Send the prompt to the API with any appropriate parameters. The code below shows an example in Python using the requests package.

import requests

endpoint = 'https://api.together.xyz/inference'
TOGETHER_API_KEY = os.getenv('TOGETHER_API_KEY')

res = requests.post(endpoint, json={
    "model": 'togethercomputer/RedPajama-INCITE-7B-Base',
    "prompt": """\
      Label the sentences as either "positive", "negative", "mixed", or "neutral":

      Sentence: I can say that there isn't anything I would change.
      Label: positive

      Sentence: I'm not sure about this.
      Label: neutral

      Sentence: I liked some parts but I didn't like other parts.
      Label: mixed

      Sentence: I think the background image could have been better.
      Label: negative

      Sentence: I really like it.
      Label:""",
    "top_p": 1,
    "top_k": 40,
    "temperature": 0.8,
    "max_tokens": 1,
    "repetition_penalty": 1,
}, headers={
    "Authorization": f"Bearer {TOGETHER_API_KEY}",
    "User-Agent": "<YOUR_APP_NAME>"
})
print(res.json()['output']['choices'][0]['text']) # ' positive'

Topic classification

RedPajama-INCITE-Instruct-7B can be used to classify the topic of text passages. In this guide, you will use the model to classify the topic of a news article as either World, Sports, Business, or Sci/Tech.

Begin the prompt with an instruction describing the task.

Given a news article, classify its topic.
Possible labels: 1. World 2. Sports 3. Business 4. Sci/Tech

After the instruction, provide a few examples with known labels.

Article: A nearby star thought to harbor comets and asteroids now appears to be home to planets, too.
Label: Sci/Tech

Article: Soaring crude prices plus worries about the economy and the outlook for earnings are expected to hang over the stock market next week during the depth of the summer doldrums.
Label: Business

Finally, append the tweet that the model should classify and prompt the model to complete the label.

Article: Murtagh a stickler for success Northeastern field hockey coach Cheryl Murtagh doesn't want the glare of the spotlight that shines on her to detract from a team that has been the America East champion for the past three years and has been to the NCAA tournament 13 times.
Label:

Send the prompt to the API with any appropriate parameters. The code below shows an example in Python using the requests package.

import requests

endpoint = 'https://api.together.xyz/inference'

res = requests.post(endpoint, json={
    "model": "togethercomputer/RedPajama-INCITE-Instruct-7B",
    "prompt": """
        Given a news article, classify its topic.
        Possible labels: 1. World 2. Sports 3. Business 4. Sci/Tech

        Article: A nearby star thought to harbor comets and asteroids now appears to be home to planets, too.
        Label: Sci/Tech

        Article: Soaring crude prices plus worries about the economy and the outlook for earnings are expected to hang over the stock market next week during the depth of the summer doldrums.
        Label: Business

        Article: Murtagh a stickler for success Northeastern field hockey coach Cheryl Murtagh doesn't want the glare of the spotlight that shines on her to detract from a team that has been the America East champion for the past three years and has been to the NCAA tournament 13 times.
        Label: """,
    "top_p": 1,
    "top_k": 40,
    "temperature": 0.8,
    "max_tokens": 1,
    "repetition_penalty": 1,
}, headers={
    "Authorization": "Bearer <YOUR_API_KEY>",
    "User-Agent": "<YOUR_APP_NAME>"
})
print(res.json())

Question answering

RedPajama-INCITE-Instruct-7B can be used to answer questions with reasoning on a user-provided context.

Begin the prompt by providing the context.

Daniel travelled to the kitchen.
Mary grabbed the milk.
Daniel went back to the hallway.
John moved to the kitchen.
Daniel travelled to the office.
John grabbed the apple.
John journeyed to the garden.
John dropped the apple.
John moved to the hallway.
Mary dropped the milk.
Daniel went back to the bathroom.
Mary grabbed the milk there.
Mary went back to the garden.
Mary went to the hallway.
Mary left the milk.
John journeyed to the bedroom.

Then, add a question followed by "Question:" and prompt the model to answer the question.

Question: Where was the milk before the hallway?
Answer:

Sample response:

Answer: garden

Send the prompt to the API with any appropriate parameters. The code below shows an example in Python using the requests package.

import requests

endpoint = 'https://api.together.xyz/inference'

res = requests.post(endpoint, json={
    "model": "togethercomputer/RedPajama-INCITE-7B-Instruct",
    "prompt": """\
        Daniel travelled to the kitchen.
        Mary grabbed the milk.
        Daniel went back to the hallway.
        John moved to the kitchen.
        Daniel travelled to the office.
        John grabbed the apple.
        John journeyed to the garden.
        John dropped the apple.
        John moved to the hallway.
        Mary dropped the milk.
        Daniel went back to the bathroom.
        Mary grabbed the milk there.
        Mary went back to the garden.
        Mary went to the hallway.
        Mary left the milk.
        John journeyed to the bedroom.
        Question: Where was the milk before the hallway?
				Answer: """,
    "top_p": 1,
    "top_k": 40,
    "temperature": 0.1,
    "max_tokens": 1,
    "repetition_penalty": 1,
}, headers={
    "Authorization": "Bearer <YOUR_API_KEY>",
    "User-Agent": "<YOUR_APP_NAME>"
})
print(res.json())

Troubleshooting code

You can use RedPajama-INCITE-Chat-7B for troubleshooting your code.

For example, begin the prompt by providing an error message you have.

 I got "ImportError: No module named matplotlib", how to solve it?

Sample response

Make sure that matplotlib is installed on your computer. You can check by running the following command in your terminal:
```
pip install matplotlib
```
If the above command does not work, try the following:
```
sudo apt-get install python-pip
pip install matplotlib
```

Send the prompt to the API with any appropriate parameters. The code below shows an example in Python using the requests package.

import requests

url = "https://api.together.xyz/inference"

payload = {
    "model": "togethercomputer/togethercomputer/RedPajama-INCITE-7B-Chat",
    "prompt": "I got \"ImportError: No module named matplotlib\", how to solve it?",
    "max_tokens": 128,
    "stop": ".",
    "temperature": 0.1,
    "top_p": 0.7,
    "top_k": 50,
    "repetition_penalty": 1
}
headers = {
    "accept": "application/json",
    "content-type": "application/json",
    "Authorization": "Bearer <YOUR_API_KEY>",
  	"User-Agent": "<YOUR_APP_NAME>",
}    

response = requests.post(url, json=payload, headers=headers)

print(response.text)

Writing Python functions

You can use RedPajama-INCITE-Chat-7B for writing a Python function.

For example, begin the prompt by providing an error message you have.

Generate a Python function to calculate the factorial of a number.

Sample response

Here's a Python function to calculate the factorial of a number:
```
def factorial(n):
    if n == 0:
        return 1
    else:
        return n * factorial(n - 1)
```
This function takes a numeric argument n and returns the factorial of n, which is the product of all integers i such that 0 <= i < n. The base case is when n is 0, which has a factorial of 1. The recursive case calculates the product of all integers i such that 0 <= i < n, including n. n.

Send the prompt to the API with any appropriate parameters. The code below shows an example in Python using the requests package.

import requests

url = "https://api.together.xyz/inference"

payload = {
    "model": "togethercomputer/togethercomputer/RedPajama-INCITE-7B-Chat",
    "prompt": "Generate a Python function to calculate the factorial of a number.",
    "max_tokens": 256,
    "stop": ".",
    "temperature": 0.1,
    "top_p": 0.7,
    "top_k": 50,
    "repetition_penalty": 1
}
headers = {
    "accept": "application/json",
    "content-type": "application/json",
    "Authorization": "Bearer <YOUR_API_KEY>",
  	"User-Agent": "<YOUR_APP_NAME>",
}    

response = requests.post(url, json=payload, headers=headers)

print(response.text)

HTML Page

You can use RedPajama-INCITE-Chat-7B for generating a simple HTML page.

For example, begin the prompt by providing a task you want to perform in HTML

Generate a simple HTML page showing "Hello world!"

Sample response

Here's an example of a simple HTML page with the text "Hello World!":
```
<!DOCTYPE html>
<html>
  <head>
    <title>Hello World!</title>
  </head>
  <body>
    <h1>Hello World!</h1>
  </body>
</html>
```

Send the prompt to the API with any appropriate parameters. The code below shows an example in Python using the requests package.

import requests

url = "https://api.together.xyz/inference"

payload = {
    "model": "togethercomputer/togethercomputer/RedPajama-INCITE-7B-Chat",
    "prompt": "Generate a simple HTML page showing \"Hello world!\"",
    "max_tokens": 256,
    "stop": ".",
    "temperature": 0.1,
    "top_p": 0.7,
    "top_k": 50,
    "repetition_penalty": 1
}
headers = {
    "accept": "application/json",
    "content-type": "application/json",
    "Authorization": "Bearer <YOUR_API_KEY>",
  	"User-Agent": "<YOUR_APP_NAME>",
}    

response = requests.post(url, json=payload, headers=headers)

print(response.text)