deepseek-ai/deepseek-math-7b-instruct – Run with an API on Replicate

deepseek-ai / deepseek-math-7b-instruct

Pushing the Limits of Mathematical Reasoning in Open Language Models - Instruct model

Cold

Public
1.6K runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

text

string

Shift + Return to add a new line

what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \boxed{}.what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \boxed{}.

Input text.

Default: "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \boxed{}."

max_new_tokens

integer

The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt.

Default: 100

temperature

number

The value used to modulate the next token probabilities.

Default: 1

top_k

integer

The number of highest probability vocabulary tokens to keep for top-k-filtering.

Default: 50

top_p

number

If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.

Default: 0.9

Run this model in Node.js with one line of code:

npx create-replicate --model=deepseek-ai/deepseek-math-7b-instruct

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run deepseek-ai/deepseek-math-7b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "deepseek-ai/deepseek-math-7b-instruct:8328993709e75f2e6417d9ac24a1330961545f6d05d1ab13cdfdd21c00cb1a6e",
  {
    input: {
      text: "what is the integral of x^2 from 0 to 2?\\nPlease reason step by step, and put your final answer within \\boxed{}.",
      top_k: 50,
      top_p: 0.9,
      temperature: 1,
      max_new_tokens: 500
    }
  }
);
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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run deepseek-ai/deepseek-math-7b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "deepseek-ai/deepseek-math-7b-instruct:8328993709e75f2e6417d9ac24a1330961545f6d05d1ab13cdfdd21c00cb1a6e",
    input={
        "text": "what is the integral of x^2 from 0 to 2?\\nPlease reason step by step, and put your final answer within \\boxed{}.",
        "top_k": 50,
        "top_p": 0.9,
        "temperature": 1,
        "max_new_tokens": 500
    }
)

# The deepseek-ai/deepseek-math-7b-instruct model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/deepseek-ai/deepseek-math-7b-instruct/api#output-schema
    print(item, end="")

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run deepseek-ai/deepseek-math-7b-instruct 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": "8328993709e75f2e6417d9ac24a1330961545f6d05d1ab13cdfdd21c00cb1a6e",
    "input": {
      "text": "what is the integral of x^2 from 0 to 2?\\\\nPlease reason step by step, and put your final answer within \\\\boxed{}.",
      "top_k": 50,
      "top_p": 0.9,
      "temperature": 1,
      "max_new_tokens": 500
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

To find the integral of x^2 with respect to x, we use the power rule of integration, which states that the integral of x^n with respect to x is (x^(n+1))/(n+1) + C, where n is a constant and C is the constant of integration. So, the integral of x^2 with respect to x is (x^(2+1))/(2+1) + C = (x^3)/3 + C. Now, we need to evaluate this integral from 0 to 2. We do this by plugging in the limits of integration: [(2^3)/3 + C] - [(0^3)/3 + C] = (8/3) - (0/3) = 8/3. So, the integral of x^2 from 0 to 2 is 8/3. The answer is $\boxed{\frac{8}{3}}$.

{
  "completed_at": "2024-02-11T12:06:34.717213Z",
  "created_at": "2024-02-11T12:06:24.935283Z",
  "data_removed": false,
  "error": null,
  "id": "5ub75m3bktk6q2rtscaqy2fqnq",
  "input": {
    "text": "what is the integral of x^2 from 0 to 2?\\nPlease reason step by step, and put your final answer within \\boxed{}.",
    "top_k": 50,
    "top_p": 0.9,
    "temperature": 1,
    "max_new_tokens": 500
  },
  "logs": null,
  "metrics": {
    "predict_time": 9.709549,
    "total_time": 9.78193
  },
  "output": [
    " ",
    "To ",
    "find ",
    "the ",
    "integral ",
    "of ",
    "",
    "",
    "x^2 ",
    "with ",
    "respect ",
    "to ",
    "",
    "x, ",
    "we ",
    "use ",
    "the ",
    "power ",
    "rule ",
    "of ",
    "",
    "integration, ",
    "which ",
    "states ",
    "that ",
    "the ",
    "integral ",
    "of ",
    "",
    "",
    "x^n ",
    "with ",
    "respect ",
    "to ",
    "x ",
    "is ",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "(x^(n+1))/(n+1) ",
    "+ ",
    "",
    "C, ",
    "where ",
    "n ",
    "is ",
    "a ",
    "constant ",
    "and ",
    "C ",
    "is ",
    "the ",
    "constant ",
    "of ",
    "",
    "integration.\n",
    "\n",
    "",
    "",
    "So, ",
    "the ",
    "integral ",
    "of ",
    "",
    "",
    "x^2 ",
    "with ",
    "respect ",
    "to ",
    "x ",
    "is ",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "(x^(2+1))/(2+1) ",
    "+ ",
    "C ",
    "= ",
    "",
    "",
    "",
    "",
    "",
    "(x^3)/3 ",
    "+ ",
    "",
    "C.\n",
    "\n",
    "",
    "",
    "Now, ",
    "we ",
    "need ",
    "to ",
    "evaluate ",
    "this ",
    "integral ",
    "from ",
    "",
    "0 ",
    "to ",
    "",
    "",
    "2. ",
    "We ",
    "do ",
    "this ",
    "by ",
    "plugging ",
    "in ",
    "the ",
    "limits ",
    "of ",
    "",
    "integration:\n",
    "\n",
    "",
    "",
    "",
    "",
    "",
    "",
    "[(2^3)/3 ",
    "+ ",
    "",
    "C] ",
    "- ",
    "",
    "",
    "",
    "",
    "",
    "[(0^3)/3 ",
    "+ ",
    "",
    "C] ",
    "= ",
    "",
    "",
    "",
    "",
    "(8/3) ",
    "- ",
    "",
    "",
    "",
    "",
    "(0/3) ",
    "= ",
    "",
    "",
    "",
    "",
    "8/3.\n",
    "\n",
    "",
    "",
    "So, ",
    "the ",
    "integral ",
    "of ",
    "",
    "",
    "x^2 ",
    "from ",
    "",
    "0 ",
    "to ",
    "",
    "2 ",
    "is ",
    "",
    "",
    "",
    "",
    "8/3.\n",
    "",
    "The ",
    "answer ",
    "is ",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "$\\boxed{\\frac{8}{3}}$."
  ],
  "started_at": "2024-02-11T12:06:25.007664Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/56afhokyt44ocxi3ur3zlj2pksc77wypchhfsvuothl5l477pspa",
    "get": "https://api.replicate.com/v1/predictions/5ub75m3bktk6q2rtscaqy2fqnq",
    "cancel": "https://api.replicate.com/v1/predictions/5ub75m3bktk6q2rtscaqy2fqnq/cancel"
  },
  "version": "8328993709e75f2e6417d9ac24a1330961545f6d05d1ab13cdfdd21c00cb1a6e"
}

Generated in

9.7 seconds

Tweak it Report

Run time and cost

This model costs approximately $1.45 to run on Replicate, or 0 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 25 minutes. The predict time for this model varies significantly based on the inputs.

Readme

$table$

Demo for deepseek-math-7b-base: https://replicate.com/cjwbw/deepseek-math-7b-base

Introduction

DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens. DeepSeekMath 7B has achieved an impressive score of 51.7% on the competition-level MATH benchmark without relying on external toolkits and voting techniques, approaching the performance level of Gemini-Ultra and GPT-4. For research purposes, we release checkpoints of base, instruct, and RL models to the public.

$table$

License

This code repository is licensed under the MIT License. The use of DeepSeekMath models is subject to the Model License. DeepSeekMath supports commercial use.

See the LICENSE-CODE and LICENSE-MODEL for more details.

Citation

@misc{deepseek-math,
  author = {Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y.K. Li, Y. Wu, Daya Guo},
  title = {DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models},
  journal = {CoRR},
  volume = {abs/2402.03300},
  year = {2024},
  url = {https://arxiv.org/abs/2402.03300},
}

Contact

If you have any questions, please raise an issue or contact us at service@deepseek.com.