tomasmcm / starling-lm-7b-alpha

Source: berkeley-nest/Starling-LM-7B-alpha ✦ Quant: TheBloke/Starling-LM-7B-alpha-AWQ ✦ An open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF)

Cold

Public
61.3K runs
L40S
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99

Model

tomasmcm/starling-lm-7b-alpha:1cee1365

pibjhrlb5y36oo6xfwvj264qaq

Status

Succeeded

Source

Web

Hardware

A40

Total duration

2.9s

Created

over 1 year ago

Input

top_k: -1
top_p: 0.95
prompt: GPT4 Correct User: Tell me about AI<|end_of_turn|>GPT4 Correct Assistant:
max_tokens: 128
temperature: 0.8
presence_penalty: 0
frequency_penalty: 0

{
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "GPT4 Correct User: Tell me about AI<|end_of_turn|>GPT4 Correct Assistant:",
  "max_tokens": 128,
  "temperature": 0.8,
  "presence_penalty": 0,
  "frequency_penalty": 0
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run tomasmcm/starling-lm-7b-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99",
  {
    input: {
      top_k: -1,
      top_p: 0.95,
      prompt: "GPT4 Correct User: Tell me about AI<|end_of_turn|>GPT4 Correct Assistant:",
      max_tokens: 128,
      temperature: 0.8,
      presence_penalty: 0,
      frequency_penalty: 0
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run tomasmcm/starling-lm-7b-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99",
    input={
        "top_k": -1,
        "top_p": 0.95,
        "prompt": "GPT4 Correct User: Tell me about AI<|end_of_turn|>GPT4 Correct Assistant:",
        "max_tokens": 128,
        "temperature": 0.8,
        "presence_penalty": 0,
        "frequency_penalty": 0
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run tomasmcm/starling-lm-7b-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99",
    "input": {
      "top_k": -1,
      "top_p": 0.95,
      "prompt": "GPT4 Correct User: Tell me about AI<|end_of_turn|>GPT4 Correct Assistant:",
      "max_tokens": 128,
      "temperature": 0.8,
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Artificial Intelligence (AI) refers to the development of computer systems or software that are capable of performing tasks that would typically require human intelligence. These tasks can include learning, problem-solving, reasoning, understanding natural language, perception, and decision-making. AI is a rapidly growing field that encompasses various sub-disciplines, including machine learning, deep learning, and neural networks. Machine learning is a subset of AI that focuses on the development of algorithms and models that enable computers to learn from data without being explicitly programmed. It involves the use of statistical techniques to identify patterns in data and make predictions or decisions

Generated in

2.8 seconds

Tweak it Share Report

Prediction

tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99

Model

tomasmcm/starling-lm-7b-alpha:1cee1365

ql25kttbj4y3apy4uiswsh7jr4

Status

Succeeded

Source

Web

Hardware

A40

Total duration

2.9s

Created

over 1 year ago

Input

top_k: -1
top_p: 0.95
prompt: Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:
max_tokens: 128
temperature: 0.8
presence_penalty: 0
frequency_penalty: 0

{
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:",
  "max_tokens": 128,
  "temperature": 0.8,
  "presence_penalty": 0,
  "frequency_penalty": 0
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run tomasmcm/starling-lm-7b-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99",
  {
    input: {
      top_k: -1,
      top_p: 0.95,
      prompt: "Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:",
      max_tokens: 128,
      temperature: 0.8,
      presence_penalty: 0,
      frequency_penalty: 0
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run tomasmcm/starling-lm-7b-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99",
    input={
        "top_k": -1,
        "top_p": 0.95,
        "prompt": "Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:",
        "max_tokens": 128,
        "temperature": 0.8,
        "presence_penalty": 0,
        "frequency_penalty": 0
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run tomasmcm/starling-lm-7b-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "tomasmcm/starling-lm-7b-alpha:1cee13652378fac04fe10dedd4c15d3024a0958c3e52f97a1aa7c4d05b99ef99",
    "input": {
      "top_k": -1,
      "top_p": 0.95,
      "prompt": "Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:",
      "max_tokens": 128,
      "temperature": 0.8,
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Here is an example of how to implement quicksort in C++: ```cpp #include <iostream> using namespace std; void quickSort(int arr[], int left, int right) { int i = left, j = right; int tmp; int pivot = arr[(left + right) / 2]; while (i <= j) { while (arr[i] < pivot) i++; while (arr[j] > pivot) j--; if (i <= j

Generated in

2.8 seconds

Tweak it Share Report