nateraw/codellama-7b-instruct-hf | Run with an API on Replicate

nateraw / codellama-7b-instruct-hf

Cold

Public
73 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

message

*string

Shift + Return to add a new line

Write a function to load a csv file and find the 3 day rolling average of the "profit" column using the "date" column.Write a function to load a csv file and find the 3 day rolling average of the "profit" column using the "date" column.

max_new_tokens

integer

The maximum number of tokens the model should generate as output.

Default: 256

temperature

number

The value used to modulate the next token probabilities.

Default: 1

top_p

number

A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).

Default: 1

top_k

integer

The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).

Default: 50

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

npx create-replicate --model=nateraw/codellama-7b-instruct-hf

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 nateraw/codellama-7b-instruct-hf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nateraw/codellama-7b-instruct-hf:efe614f6aa2d04c1e153dc33e4bc54a3ce97df8f3da7021d15a79233face5c30",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      message: "Write a function to load a csv file and find the 3 day rolling average of the \"profit\" column using the \"date\" column.",
      temperature: 1,
      max_new_tokens: 1024
    }
  }
);

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 nateraw/codellama-7b-instruct-hf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/codellama-7b-instruct-hf:efe614f6aa2d04c1e153dc33e4bc54a3ce97df8f3da7021d15a79233face5c30",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "message": "Write a function to load a csv file and find the 3 day rolling average of the \"profit\" column using the \"date\" column.",
        "temperature": 1,
        "max_new_tokens": 1024
    }
)

# The nateraw/codellama-7b-instruct-hf 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/nateraw/codellama-7b-instruct-hf/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 nateraw/codellama-7b-instruct-hf 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": "nateraw/codellama-7b-instruct-hf:efe614f6aa2d04c1e153dc33e4bc54a3ce97df8f3da7021d15a79233face5c30",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "message": "Write a function to load a csv file and find the 3 day rolling average of the \\"profit\\" column using the \\"date\\" column.",
      "temperature": 1,
      "max_new_tokens": 1024
    }
  }' \
  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 you can read in a csv file and calculate the 3 day rolling average of the "profit" column using the "date" column in Python: ``` import pandas as pd # Read in the csv file df = pd.read_csv('your_data.csv') # Calculate the 3 day rolling average of the "profit" column using the "date" column df['3_day_rolling_average'] = df['profit'].rolling(window=3).mean() # Print the results print(df) ``` This will give you the 3 day rolling average of the "profit" column for each row in the data frame. Alternatively, you can also use the `rolling_mean` function from the `pandas` library: ``` df['3_day_rolling_average'] = df.rolling_mean(window=3, column='profit', date_column='date') ``` This will give you the same result as the previous code.

{
  "completed_at": "2023-09-19T05:45:45.134834Z",
  "created_at": "2023-09-19T05:45:29.123023Z",
  "data_removed": false,
  "error": null,
  "id": "mv356a3bobm43ngw7rt6toz7ay",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "message": "Write a function to load a csv file and find the 3 day rolling average of the \"profit\" column using the \"date\" column.",
    "temperature": 1,
    "max_new_tokens": 1024
  },
  "logs": "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.",
  "metrics": {
    "predict_time": 14.911304,
    "total_time": 16.011811
  },
  "output": [
    "",
    " ",
    "Here ",
    "is ",
    "an ",
    "example ",
    "of ",
    "how ",
    "you ",
    "can ",
    "read ",
    "in ",
    "a ",
    "csv ",
    "file ",
    "and ",
    "calculate ",
    "the ",
    "",
    "3 ",
    "day ",
    "rolling ",
    "average ",
    "of ",
    "the ",
    "",
    "",
    "",
    "\"profit\" ",
    "column ",
    "using ",
    "the ",
    "",
    "",
    "\"date\" ",
    "column ",
    "in ",
    "",
    "Python:\n",
    "",
    "```\n",
    "",
    "import ",
    "pandas ",
    "as ",
    "pd\n",
    "\n",
    "",
    "# ",
    "Read ",
    "in ",
    "the ",
    "csv ",
    "file\n",
    "",
    "df ",
    "= ",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "pd.read_csv('your_data.csv')\n",
    "\n",
    "",
    "# ",
    "",
    "Calculate ",
    "the ",
    "",
    "3 ",
    "day ",
    "rolling ",
    "average ",
    "of ",
    "the ",
    "",
    "",
    "",
    "\"profit\" ",
    "column ",
    "using ",
    "the ",
    "",
    "",
    "\"date\" ",
    "column\n",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "df['3_day_rolling_average'] ",
    "= ",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "df['profit'].rolling(window=3).mean()\n",
    "\n",
    "",
    "# ",
    "Print ",
    "the ",
    "results\n",
    "",
    "",
    "",
    "",
    "print(df)\n",
    "",
    "```\n",
    "",
    "This ",
    "will ",
    "give ",
    "you ",
    "the ",
    "",
    "3 ",
    "day ",
    "rolling ",
    "average ",
    "of ",
    "the ",
    "",
    "",
    "",
    "\"profit\" ",
    "column ",
    "for ",
    "each ",
    "row ",
    "in ",
    "the ",
    "data ",
    "",
    "frame.\n",
    "\n",
    "",
    "",
    "",
    "",
    "Alternatively, ",
    "you ",
    "can ",
    "also ",
    "use ",
    "the ",
    "",
    "",
    "",
    "",
    "`rolling_mean` ",
    "function ",
    "from ",
    "the ",
    "",
    "",
    "`pandas` ",
    "",
    "library:\n",
    "",
    "```\n",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "df['3_day_rolling_average'] ",
    "= ",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "df.rolling_mean(window=3, ",
    "",
    "",
    "",
    "",
    "column='profit', ",
    "",
    "",
    "",
    "",
    "",
    "date_column='date')\n",
    "",
    "```\n",
    "",
    "This ",
    "will ",
    "give ",
    "you ",
    "the ",
    "same ",
    "result ",
    "as ",
    "the ",
    "previous ",
    "",
    "",
    "code."
  ],
  "started_at": "2023-09-19T05:45:30.223530Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/mv356a3bobm43ngw7rt6toz7ay",
    "cancel": "https://api.replicate.com/v1/predictions/mv356a3bobm43ngw7rt6toz7ay/cancel"
  },
  "version": "efe614f6aa2d04c1e153dc33e4bc54a3ce97df8f3da7021d15a79233face5c30"
}

Generated in

14.9 seconds

Tweak it Report View full prediction

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.