kcaverly/deepseek-coder-33b-instruct-gguf – Run with an API on Replicate

kcaverly / deepseek-coder-33b-instruct-gguf

A quantized 33B parameter language model from Deepseek for SOTA repository level code completion

Cold

Public
3.2K runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.

Instruction for model

system_prompt

string

Shift + Return to add a new line

You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.

System prompt for the model, helps guides model behaviour.

Default: "You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer."

prompt_template

string

Shift + Return to add a new line

{system_prompt}/n### Instruction: {prompt}/n### Response: {system_prompt}/n### Instruction: {prompt}/n### Response: 

Template to pass to model. Override if you are providing multi-turn instructions.

Default: "{system_prompt}/n### Instruction: {prompt}/n### Response: "

max_new_tokens

integer

Maximum new tokens to generate.

Default: -1

repeat_penalty

number

This parameter plays a role in controlling the behavior of an AI language model during conversation or text generation. Its purpose is to discourage the model from repeating itself too often by increasing the likelihood of following up with different content after each response. By adjusting this parameter, users can influence the model's tendency to either stay within familiar topics (lower penalty) or explore new ones (higher penalty). For instance, setting a high repeat penalty might result in more varied and dynamic conversations, whereas a low penalty could be suitable for scenarios where consistency and predictability are preferred.

Default: 1.1

temperature

number

This parameter used to control the 'warmth' or responsiveness of an AI model based on the LLaMA architecture. It adjusts how likely the model is to generate new, unexpected information versus sticking closely to what it has been trained on. A higher value for this parameter can lead to more creative and diverse responses, while a lower value results in safer, more conservative answers that are closer to those found in its training data. This parameter is particularly useful when fine-tuning models for specific tasks where you want to balance between generating novel insights and maintaining accuracy and coherence.

Default: 0.8

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

npx create-replicate --model=kcaverly/deepseek-coder-33b-instruct-gguf

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 kcaverly/deepseek-coder-33b-instruct-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "kcaverly/deepseek-coder-33b-instruct-gguf:ea964345066a8868e43aca432f314822660b72e29cab6b4b904b779014fe58fd",
  {
    input: {
      prompt: "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
      temperature: 0.8,
      system_prompt: "You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.",
      max_new_tokens: -1,
      repeat_penalty: 1.1,
      prompt_template: "{system_prompt}/n### Instruction: {prompt}/n### Response: "
    }
  }
);

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 kcaverly/deepseek-coder-33b-instruct-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "kcaverly/deepseek-coder-33b-instruct-gguf:ea964345066a8868e43aca432f314822660b72e29cab6b4b904b779014fe58fd",
    input={
        "prompt": "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
        "temperature": 0.8,
        "system_prompt": "You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.",
        "max_new_tokens": -1,
        "repeat_penalty": 1.1,
        "prompt_template": "{system_prompt}/n### Instruction: {prompt}/n### Response: "
    }
)

# The kcaverly/deepseek-coder-33b-instruct-gguf 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/kcaverly/deepseek-coder-33b-instruct-gguf/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 kcaverly/deepseek-coder-33b-instruct-gguf 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": "ea964345066a8868e43aca432f314822660b72e29cab6b4b904b779014fe58fd",
    "input": {
      "prompt": "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
      "temperature": 0.8,
      "system_prompt": "You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.",
      "max_new_tokens": -1,
      "repeat_penalty": 1.1,
      "prompt_template": "{system_prompt}/n### Instruction: {prompt}/n### Response: "
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

```rust enum PredictionStatus { Starting, InProgress, Completed, } ```

{
  "completed_at": "2023-12-11T01:49:28.593785Z",
  "created_at": "2023-12-11T01:49:27.007630Z",
  "data_removed": false,
  "error": null,
  "id": "cdpmejdbazlj6jmhb243pw64ki",
  "input": {
    "prompt": "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
    "temperature": 0.8,
    "system_prompt": "You are an AI programming assistant, utilizing the Deepseek Code model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.",
    "max_new_tokens": -1,
    "repeat_penalty": 1.1,
    "prompt_template": "{system_prompt}/n### Instruction: {prompt}/n### Response: "
  },
  "logs": "Llama.generate: prefix-match hit\nllama_print_timings:        load time =     279.99 ms\nllama_print_timings:      sample time =       4.17 ms /    29 runs   (    0.14 ms per token,  6954.44 tokens per second)\nllama_print_timings: prompt eval time =     219.64 ms /    15 tokens (   14.64 ms per token,    68.29 tokens per second)\nllama_print_timings:        eval time =    1226.00 ms /    28 runs   (   43.79 ms per token,    22.84 tokens per second)\nllama_print_timings:       total time =    1501.62 ms",
  "metrics": {
    "predict_time": 1.508145,
    "total_time": 1.586155
  },
  "output": [
    "\n",
    "```",
    "rust",
    "\n",
    "enum",
    " Pred",
    "iction",
    "Status",
    " {",
    "\n",
    "   ",
    " Starting",
    ",",
    "\n",
    "   ",
    " In",
    "Progress",
    ",",
    "\n",
    "   ",
    " Comple",
    "ted",
    ",",
    "\n",
    "}",
    "\n",
    "```",
    "\n",
    ""
  ],
  "started_at": "2023-12-11T01:49:27.085640Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/predictions/cdpmejdbazlj6jmhb243pw64ki",
    "get": "https://api.replicate.com/v1/predictions/cdpmejdbazlj6jmhb243pw64ki",
    "cancel": "https://api.replicate.com/v1/predictions/cdpmejdbazlj6jmhb243pw64ki/cancel"
  },
  "version": "ea964345066a8868e43aca432f314822660b72e29cab6b4b904b779014fe58fd"
}

Generated in

1.5 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.0025 to run on Replicate, or 400 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 3 seconds.

Readme

TheBloke’s quantized version of Deepseek’s Coder 33B Instruct model in GGUF format. The full model card can be found here.

Specifically, this is the deepseek-coder-33b-instruct.Q5_K_M.gguf model, with a 16k context window.