tomasmcm/pandalyst-13b-v1.0 | Run with an API on Replicate

tomasmcm / pandalyst-13b-v1.0

Source: pipizhao/Pandalyst_13B_V1.0 ✦ Quant: TheBloke/Pandalyst_13B_V1.0-AWQ ✦ Pandalyst: A large language model for mastering data analysis using pandas

Cold

Public
21 runs
L40S
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Dataframe Name: Career summary, with 43 rows and 9 columns.
Description: This is a table about Gabriel Furlán: Career summary
Columns: Season, Series, Team, Races, Wins, Poles, Podiums, Points, Position
Here are the descriptions of the columns of the dataframe:
{"Column Name": "Season", "Type": "int", "MIN": 1984, "MAX": 2011}
{"Column Name": "Wins", "Type": "string", "Enumerated Values": ["0", "6", "2", "3", "7", "?", "5", "1"]}
{"Column Name": "Position", "Type": "string", "Enumerated Values": ["9th", "18th", "2nd", "10th", "N/A", "13th", "7th", "4th", "6th", "3rd", "8th", "?", "1st", "16th", "11th", "19th", "5th"]}
{"Column Name": "Podiums", "Type": "string", "Enumerated Values": ["9", "0", "3", "7", "?", "5", "1", "4"]}
{"Column Name": "Team", "Type": "string", "Enumerated Values": ["INI Competición", "Junior Team", "Forti Corse", "GF Motorsport", "GF Racing", "Toyota Team Argentina", "Gustavo Sommi", "Ford", "DTA", "Maldonado Competición", "Sommi-Zanón", "Bainotti Dowen Pagio", "Scuderia 111", "Jolly Club"]}
{"Column Name": "Races", "Type": "string", "Enumerated Values": ["9", "8", "13", "2", "7", "14", "18", "?", "5", "1", "12", "4", "11"]}
{"Column Name": "Points", "Type": "string", "Enumerated Values": ["39", "90", "67", "0", "35.5", "79", "78", "52", "N/A", "16", "38", "26", "65", "144", "1", "139", "175", "42", "32", "46"]}
{"Column Name": "Series", "Type": "string", "Enumerated Values": ["Monaco Grand Prix Formula Three", "TC 2000", "Fórmula 2 Codasur", "Stock Car Brasil", "Formula Renault Argentina", "International Formula 3000", "Super Turismo V8", "World Cup Formula 3000", "Top Race V6", "Top Race V6 Copa América", "Formula Three Sudamericana", "Italian Formula Three", "TC 2000 Endurance series"]}
{"Column Name": "Poles", "Type": "string", "Enumerated Values": ["0", "2", "3", "?", "5", "1", "4"]}
Question: 
Can we analyze the correlation between the number of races Gabriel Furlán participated in each season and the number of wins he achieved in the same season?

### Response:
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Dataframe Name: Career summary, with 43 rows and 9 columns.
Description: This is a table about Gabriel Furlán: Career summary
Columns: Season, Series, Team, Races, Wins, Poles, Podiums, Points, Position
Here are the descriptions of the columns of the dataframe:
{"Column Name": "Season", "Type": "int", "MIN": 1984, "MAX": 2011}
{"Column Name": "Wins", "Type": "string", "Enumerated Values": ["0", "6", "2", "3", "7", "?", "5", "1"]}
{"Column Name": "Position", "Type": "string", "Enumerated Values": ["9th", "18th", "2nd", "10th", "N/A", "13th", "7th", "4th", "6th", "3rd", "8th", "?", "1st", "16th", "11th", "19th", "5th"]}
{"Column Name": "Podiums", "Type": "string", "Enumerated Values": ["9", "0", "3", "7", "?", "5", "1", "4"]}
{"Column Name": "Team", "Type": "string", "Enumerated Values": ["INI Competición", "Junior Team", "Forti Corse", "GF Motorsport", "GF Racing", "Toyota Team Argentina", "Gustavo Sommi", "Ford", "DTA", "Maldonado Competición", "Sommi-Zanón", "Bainotti Dowen Pagio", "Scuderia 111", "Jolly Club"]}
{"Column Name": "Races", "Type": "string", "Enumerated Values": ["9", "8", "13", "2", "7", "14", "18", "?", "5", "1", "12", "4", "11"]}
{"Column Name": "Points", "Type": "string", "Enumerated Values": ["39", "90", "67", "0", "35.5", "79", "78", "52", "N/A", "16", "38", "26", "65", "144", "1", "139", "175", "42", "32", "46"]}
{"Column Name": "Series", "Type": "string", "Enumerated Values": ["Monaco Grand Prix Formula Three", "TC 2000", "Fórmula 2 Codasur", "Stock Car Brasil", "Formula Renault Argentina", "International Formula 3000", "Super Turismo V8", "World Cup Formula 3000", "Top Race V6", "Top Race V6 Copa América", "Formula Three Sudamericana", "Italian Formula Three", "TC 2000 Endurance series"]}
{"Column Name": "Poles", "Type": "string", "Enumerated Values": ["0", "2", "3", "?", "5", "1", "4"]}
Question: 
Can we analyze the correlation between the number of races Gabriel Furlán participated in each season and the number of wins he achieved in the same season?

### Response:

Text prompt to send to the model.

max_tokens

integer

Maximum number of tokens to generate per output sequence.

Default: 128

presence_penalty

number

(minimum: -5, maximum: 5)

Float that penalizes new tokens based on whether they appear in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.

Default: 0

frequency_penalty

number

(minimum: -5, maximum: 5)

Float that penalizes new tokens based on their frequency in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.

Default: 0

temperature

number

(minimum: 0.01, maximum: 5)

Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.

Default: 0.8

top_p

number

(minimum: 0.01, maximum: 1)

Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.

Default: 0.95

top_k

integer

Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.

Default: -1

stop

string

Shift + Return to add a new line

List of strings that stop the generation when they are generated. The returned output will not contain the stop strings.

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

npx create-replicate --model=tomasmcm/pandalyst-13b-v1.0

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 tomasmcm/pandalyst-13b-v1.0 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "tomasmcm/pandalyst-13b-v1.0:49be21dfc89f89bc2753f71132dd98eaba1251423a021ce2d62b690e068819cc",
  {
    input: {
      top_k: -1,
      top_p: 0.95,
      prompt: "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nDataframe Name: Career summary, with 43 rows and 9 columns.\nDescription: This is a table about Gabriel Furlán: Career summary\nColumns: Season, Series, Team, Races, Wins, Poles, Podiums, Points, Position\nHere are the descriptions of the columns of the dataframe:\n{\"Column Name\": \"Season\", \"Type\": \"int\", \"MIN\": 1984, \"MAX\": 2011}\n{\"Column Name\": \"Wins\", \"Type\": \"string\", \"Enumerated Values\": [\"0\", \"6\", \"2\", \"3\", \"7\", \"?\", \"5\", \"1\"]}\n{\"Column Name\": \"Position\", \"Type\": \"string\", \"Enumerated Values\": [\"9th\", \"18th\", \"2nd\", \"10th\", \"N/A\", \"13th\", \"7th\", \"4th\", \"6th\", \"3rd\", \"8th\", \"?\", \"1st\", \"16th\", \"11th\", \"19th\", \"5th\"]}\n{\"Column Name\": \"Podiums\", \"Type\": \"string\", \"Enumerated Values\": [\"9\", \"0\", \"3\", \"7\", \"?\", \"5\", \"1\", \"4\"]}\n{\"Column Name\": \"Team\", \"Type\": \"string\", \"Enumerated Values\": [\"INI Competición\", \"Junior Team\", \"Forti Corse\", \"GF Motorsport\", \"GF Racing\", \"Toyota Team Argentina\", \"Gustavo Sommi\", \"Ford\", \"DTA\", \"Maldonado Competición\", \"Sommi-Zanón\", \"Bainotti Dowen Pagio\", \"Scuderia 111\", \"Jolly Club\"]}\n{\"Column Name\": \"Races\", \"Type\": \"string\", \"Enumerated Values\": [\"9\", \"8\", \"13\", \"2\", \"7\", \"14\", \"18\", \"?\", \"5\", \"1\", \"12\", \"4\", \"11\"]}\n{\"Column Name\": \"Points\", \"Type\": \"string\", \"Enumerated Values\": [\"39\", \"90\", \"67\", \"0\", \"35.5\", \"79\", \"78\", \"52\", \"N/A\", \"16\", \"38\", \"26\", \"65\", \"144\", \"1\", \"139\", \"175\", \"42\", \"32\", \"46\"]}\n{\"Column Name\": \"Series\", \"Type\": \"string\", \"Enumerated Values\": [\"Monaco Grand Prix Formula Three\", \"TC 2000\", \"Fórmula 2 Codasur\", \"Stock Car Brasil\", \"Formula Renault Argentina\", \"International Formula 3000\", \"Super Turismo V8\", \"World Cup Formula 3000\", \"Top Race V6\", \"Top Race V6 Copa América\", \"Formula Three Sudamericana\", \"Italian Formula Three\", \"TC 2000 Endurance series\"]}\n{\"Column Name\": \"Poles\", \"Type\": \"string\", \"Enumerated Values\": [\"0\", \"2\", \"3\", \"?\", \"5\", \"1\", \"4\"]}\nQuestion: \nCan we analyze the correlation between the number of races Gabriel Furlán participated in each season and the number of wins he achieved in the same season?\n\n### Response:\n",
      max_tokens: 512,
      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

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 tomasmcm/pandalyst-13b-v1.0 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "tomasmcm/pandalyst-13b-v1.0:49be21dfc89f89bc2753f71132dd98eaba1251423a021ce2d62b690e068819cc",
    input={
        "top_k": -1,
        "top_p": 0.95,
        "prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nDataframe Name: Career summary, with 43 rows and 9 columns.\nDescription: This is a table about Gabriel Furlán: Career summary\nColumns: Season, Series, Team, Races, Wins, Poles, Podiums, Points, Position\nHere are the descriptions of the columns of the dataframe:\n{\"Column Name\": \"Season\", \"Type\": \"int\", \"MIN\": 1984, \"MAX\": 2011}\n{\"Column Name\": \"Wins\", \"Type\": \"string\", \"Enumerated Values\": [\"0\", \"6\", \"2\", \"3\", \"7\", \"?\", \"5\", \"1\"]}\n{\"Column Name\": \"Position\", \"Type\": \"string\", \"Enumerated Values\": [\"9th\", \"18th\", \"2nd\", \"10th\", \"N/A\", \"13th\", \"7th\", \"4th\", \"6th\", \"3rd\", \"8th\", \"?\", \"1st\", \"16th\", \"11th\", \"19th\", \"5th\"]}\n{\"Column Name\": \"Podiums\", \"Type\": \"string\", \"Enumerated Values\": [\"9\", \"0\", \"3\", \"7\", \"?\", \"5\", \"1\", \"4\"]}\n{\"Column Name\": \"Team\", \"Type\": \"string\", \"Enumerated Values\": [\"INI Competición\", \"Junior Team\", \"Forti Corse\", \"GF Motorsport\", \"GF Racing\", \"Toyota Team Argentina\", \"Gustavo Sommi\", \"Ford\", \"DTA\", \"Maldonado Competición\", \"Sommi-Zanón\", \"Bainotti Dowen Pagio\", \"Scuderia 111\", \"Jolly Club\"]}\n{\"Column Name\": \"Races\", \"Type\": \"string\", \"Enumerated Values\": [\"9\", \"8\", \"13\", \"2\", \"7\", \"14\", \"18\", \"?\", \"5\", \"1\", \"12\", \"4\", \"11\"]}\n{\"Column Name\": \"Points\", \"Type\": \"string\", \"Enumerated Values\": [\"39\", \"90\", \"67\", \"0\", \"35.5\", \"79\", \"78\", \"52\", \"N/A\", \"16\", \"38\", \"26\", \"65\", \"144\", \"1\", \"139\", \"175\", \"42\", \"32\", \"46\"]}\n{\"Column Name\": \"Series\", \"Type\": \"string\", \"Enumerated Values\": [\"Monaco Grand Prix Formula Three\", \"TC 2000\", \"Fórmula 2 Codasur\", \"Stock Car Brasil\", \"Formula Renault Argentina\", \"International Formula 3000\", \"Super Turismo V8\", \"World Cup Formula 3000\", \"Top Race V6\", \"Top Race V6 Copa América\", \"Formula Three Sudamericana\", \"Italian Formula Three\", \"TC 2000 Endurance series\"]}\n{\"Column Name\": \"Poles\", \"Type\": \"string\", \"Enumerated Values\": [\"0\", \"2\", \"3\", \"?\", \"5\", \"1\", \"4\"]}\nQuestion: \nCan we analyze the correlation between the number of races Gabriel Furlán participated in each season and the number of wins he achieved in the same season?\n\n### Response:\n",
        "max_tokens": 512,
        "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.

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Run tomasmcm/pandalyst-13b-v1.0 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/pandalyst-13b-v1.0:49be21dfc89f89bc2753f71132dd98eaba1251423a021ce2d62b690e068819cc",
    "input": {
      "top_k": -1,
      "top_p": 0.95,
      "prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nDataframe Name: Career summary, with 43 rows and 9 columns.\\nDescription: This is a table about Gabriel Furlán: Career summary\\nColumns: Season, Series, Team, Races, Wins, Poles, Podiums, Points, Position\\nHere are the descriptions of the columns of the dataframe:\\n{\\"Column Name\\": \\"Season\\", \\"Type\\": \\"int\\", \\"MIN\\": 1984, \\"MAX\\": 2011}\\n{\\"Column Name\\": \\"Wins\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"0\\", \\"6\\", \\"2\\", \\"3\\", \\"7\\", \\"?\\", \\"5\\", \\"1\\"]}\\n{\\"Column Name\\": \\"Position\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"9th\\", \\"18th\\", \\"2nd\\", \\"10th\\", \\"N/A\\", \\"13th\\", \\"7th\\", \\"4th\\", \\"6th\\", \\"3rd\\", \\"8th\\", \\"?\\", \\"1st\\", \\"16th\\", \\"11th\\", \\"19th\\", \\"5th\\"]}\\n{\\"Column Name\\": \\"Podiums\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"9\\", \\"0\\", \\"3\\", \\"7\\", \\"?\\", \\"5\\", \\"1\\", \\"4\\"]}\\n{\\"Column Name\\": \\"Team\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"INI Competición\\", \\"Junior Team\\", \\"Forti Corse\\", \\"GF Motorsport\\", \\"GF Racing\\", \\"Toyota Team Argentina\\", \\"Gustavo Sommi\\", \\"Ford\\", \\"DTA\\", \\"Maldonado Competición\\", \\"Sommi-Zanón\\", \\"Bainotti Dowen Pagio\\", \\"Scuderia 111\\", \\"Jolly Club\\"]}\\n{\\"Column Name\\": \\"Races\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"9\\", \\"8\\", \\"13\\", \\"2\\", \\"7\\", \\"14\\", \\"18\\", \\"?\\", \\"5\\", \\"1\\", \\"12\\", \\"4\\", \\"11\\"]}\\n{\\"Column Name\\": \\"Points\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"39\\", \\"90\\", \\"67\\", \\"0\\", \\"35.5\\", \\"79\\", \\"78\\", \\"52\\", \\"N/A\\", \\"16\\", \\"38\\", \\"26\\", \\"65\\", \\"144\\", \\"1\\", \\"139\\", \\"175\\", \\"42\\", \\"32\\", \\"46\\"]}\\n{\\"Column Name\\": \\"Series\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"Monaco Grand Prix Formula Three\\", \\"TC 2000\\", \\"Fórmula 2 Codasur\\", \\"Stock Car Brasil\\", \\"Formula Renault Argentina\\", \\"International Formula 3000\\", \\"Super Turismo V8\\", \\"World Cup Formula 3000\\", \\"Top Race V6\\", \\"Top Race V6 Copa América\\", \\"Formula Three Sudamericana\\", \\"Italian Formula Three\\", \\"TC 2000 Endurance series\\"]}\\n{\\"Column Name\\": \\"Poles\\", \\"Type\\": \\"string\\", \\"Enumerated Values\\": [\\"0\\", \\"2\\", \\"3\\", \\"?\\", \\"5\\", \\"1\\", \\"4\\"]}\\nQuestion: \\nCan we analyze the correlation between the number of races Gabriel Furlán participated in each season and the number of wins he achieved in the same season?\\n\\n### Response:\\n",
      "max_tokens": 512,
      "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

```python # Prepare the data: convert "Races" and "Wins" to numerical values, and replace '?' and 'N/A' with NaN career_summary['Races'] = pd.to_numeric(career_summary['Races'], errors='coerce') career_summary['Wins'] = pd.to_numeric(career_summary['Wins'], errors='coerce') career_summary = career_summary.dropna(subset=['Races', 'Wins']) # Calculate the correlation correlation = career_summary['Races'].corr(career_summary['Wins']) print(f"The correlation between the number of races and the number of wins is {correlation}") ```

{
  "completed_at": "2024-01-31T15:09:27.653607Z",
  "created_at": "2024-01-31T15:05:53.137182Z",
  "data_removed": false,
  "error": null,
  "id": "6vo3rsdb4usn6cq2b3jmtxijp4",
  "input": {
    "top_k": -1,
    "top_p": 0.95,
    "prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nDataframe Name: Career summary, with 43 rows and 9 columns.\nDescription: This is a table about Gabriel Furlán: Career summary\nColumns: Season, Series, Team, Races, Wins, Poles, Podiums, Points, Position\nHere are the descriptions of the columns of the dataframe:\n{\"Column Name\": \"Season\", \"Type\": \"int\", \"MIN\": 1984, \"MAX\": 2011}\n{\"Column Name\": \"Wins\", \"Type\": \"string\", \"Enumerated Values\": [\"0\", \"6\", \"2\", \"3\", \"7\", \"?\", \"5\", \"1\"]}\n{\"Column Name\": \"Position\", \"Type\": \"string\", \"Enumerated Values\": [\"9th\", \"18th\", \"2nd\", \"10th\", \"N/A\", \"13th\", \"7th\", \"4th\", \"6th\", \"3rd\", \"8th\", \"?\", \"1st\", \"16th\", \"11th\", \"19th\", \"5th\"]}\n{\"Column Name\": \"Podiums\", \"Type\": \"string\", \"Enumerated Values\": [\"9\", \"0\", \"3\", \"7\", \"?\", \"5\", \"1\", \"4\"]}\n{\"Column Name\": \"Team\", \"Type\": \"string\", \"Enumerated Values\": [\"INI Competición\", \"Junior Team\", \"Forti Corse\", \"GF Motorsport\", \"GF Racing\", \"Toyota Team Argentina\", \"Gustavo Sommi\", \"Ford\", \"DTA\", \"Maldonado Competición\", \"Sommi-Zanón\", \"Bainotti Dowen Pagio\", \"Scuderia 111\", \"Jolly Club\"]}\n{\"Column Name\": \"Races\", \"Type\": \"string\", \"Enumerated Values\": [\"9\", \"8\", \"13\", \"2\", \"7\", \"14\", \"18\", \"?\", \"5\", \"1\", \"12\", \"4\", \"11\"]}\n{\"Column Name\": \"Points\", \"Type\": \"string\", \"Enumerated Values\": [\"39\", \"90\", \"67\", \"0\", \"35.5\", \"79\", \"78\", \"52\", \"N/A\", \"16\", \"38\", \"26\", \"65\", \"144\", \"1\", \"139\", \"175\", \"42\", \"32\", \"46\"]}\n{\"Column Name\": \"Series\", \"Type\": \"string\", \"Enumerated Values\": [\"Monaco Grand Prix Formula Three\", \"TC 2000\", \"Fórmula 2 Codasur\", \"Stock Car Brasil\", \"Formula Renault Argentina\", \"International Formula 3000\", \"Super Turismo V8\", \"World Cup Formula 3000\", \"Top Race V6\", \"Top Race V6 Copa América\", \"Formula Three Sudamericana\", \"Italian Formula Three\", \"TC 2000 Endurance series\"]}\n{\"Column Name\": \"Poles\", \"Type\": \"string\", \"Enumerated Values\": [\"0\", \"2\", \"3\", \"?\", \"5\", \"1\", \"4\"]}\nQuestion: \nCan we analyze the correlation between the number of races Gabriel Furlán participated in each season and the number of wins he achieved in the same season?\n\n### Response:\n",
    "max_tokens": 512,
    "temperature": 0.8,
    "presence_penalty": 0,
    "frequency_penalty": 0
  },
  "logs": "Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]\nProcessed prompts: 100%|██████████| 1/1 [00:03<00:00,  3.47s/it]\nProcessed prompts: 100%|██████████| 1/1 [00:03<00:00,  3.47s/it]\nGenerated 172 tokens in 3.4777262210845947 seconds.",
  "metrics": {
    "predict_time": 3.539034,
    "total_time": 214.516425
  },
  "output": "```python\n# Prepare the data: convert \"Races\" and \"Wins\" to numerical values, and replace '?' and 'N/A' with NaN\ncareer_summary['Races'] = pd.to_numeric(career_summary['Races'], errors='coerce')\ncareer_summary['Wins'] = pd.to_numeric(career_summary['Wins'], errors='coerce')\ncareer_summary = career_summary.dropna(subset=['Races', 'Wins'])\n\n# Calculate the correlation\ncorrelation = career_summary['Races'].corr(career_summary['Wins'])\nprint(f\"The correlation between the number of races and the number of wins is {correlation}\")\n```",
  "started_at": "2024-01-31T15:09:24.114573Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6vo3rsdb4usn6cq2b3jmtxijp4",
    "cancel": "https://api.replicate.com/v1/predictions/6vo3rsdb4usn6cq2b3jmtxijp4/cancel"
  },
  "version": "49be21dfc89f89bc2753f71132dd98eaba1251423a021ce2d62b690e068819cc"
}

Generated in

3.5 seconds

Tweak it Report View full prediction

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Pandalyst: A large language model for mastering data analysis using pandas

Github Repo: https://github.com/pipizhaoa/Pandalyst

What is Pandalyst - Pandalyst is a general large language model specifically trained to process and analyze data using the pandas library.

How is Pandalyst - Pandalyst has strong generalization capabilities for data tables in different fields and different data analysis needs.

Why is Pandalyst - Pandalyst is open source and free to use, and its small parameter size (7B/13B) allows us to easily deploy it on local PC. - Pandalyst can handle complex data tables (multiple columns and multiple rows), allowing us to enter enough context to describe our table in detail. - Pandalyst has very competitive performance, significantly outperforming models of the same size and even outperforming some of the strongest closed-source models.

News

🔥[2023/10/15] Now we can plot 📈! and much more powerful! We released Pandalyst-7B-V1.2, which was trained on CodeLlama-7b-Python and it surpasses ChatGPT-3.5 (2023/06/13), Pandalyst-7B-V1.1 and WizardCoder-Python-13B-V1.0 in our PandaTest_V1.0.
🤖️[2023/09/30] We released Pandalyst-7B-V1.1 , which was trained on CodeLlama-7b-Python and achieves the 76.1 exec@1 in our PandaTest_V1.0 and surpasses WizardCoder-Python-13B-V1.0 and ChatGPT-3.5 (2023/06/13).

Model	Checkpoint	Support plot	License
🔥Pandalyst-7B-V1.2	🤗 HF Link	✅	Llama2
Pandalyst-7B-V1.1	🤗 HF Link	❌	Llama2

Usage and Human evaluation

Please refer to Github.