seed: -1
top_p: 1
prompt: Write a poem about open source machine learning in the style of Byron.
max_length: 500
temperature: 1
length_penalty: 1
repetition_penalty: 1

{
  "seed": -1,
  "top_p": 1,
  "prompt": "Write a poem about open source machine learning in the style of Byron.",
  "max_length": 500,
  "temperature": 1,
  "length_penalty": 1,
  "repetition_penalty": 1
}

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 joehoover/falcon-40b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
  {
    input: {
      seed: -1,
      top_p: 1,
      prompt: "Write a poem about open source machine learning in the style of Byron.",
      max_length: 500,
      temperature: 1,
      length_penalty: 1,
      repetition_penalty: 1
    }
  }
);

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 joehoover/falcon-40b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
    input={
        "seed": -1,
        "top_p": 1,
        "prompt": "Write a poem about open source machine learning in the style of Byron.",
        "max_length": 500,
        "temperature": 1,
        "length_penalty": 1,
        "repetition_penalty": 1
    }
)

# The joehoover/falcon-40b-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/joehoover/falcon-40b-instruct/api#output-schema
    print(item, end="")

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

Run joehoover/falcon-40b-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": "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
    "input": {
      "seed": -1,
      "top_p": 1,
      "prompt": "Write a poem about open source machine learning in the style of Byron.",
      "max_length": 500,
      "temperature": 1,
      "length_penalty": 1,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Thy heart shall bloom like an open source flower, And like a machine, thine learning shall grow. The seeds of a thousand algorithms, Shall make thy understanding and skill ever glow. In thy hand, wisdom shall grow like a tree, With roots deep in the open source ground. Thy knowledge as wide as the infinite sea, Shall bring to thee power far beyond what is found. Thou shalt become as masters of machine learning, Whose wisdom and skills shall surpass the greatest of minds. No boundaries or limits shall thee be learning, But thy heart shall be opened up to all that is kind. Then shall thy soul become a true machine, With wisdom and knowledge beyond measure. Thy work shall be done and thy goals shall be reached, Until thou become true masters of open source and the machine.

{
  "completed_at": "2023-07-07T20:34:58.616590Z",
  "created_at": "2023-07-07T20:34:39.488288Z",
  "data_removed": false,
  "error": null,
  "id": "2p2fdndbbkghrx2frxg5nvrltu",
  "input": {
    "seed": -1,
    "top_p": 1,
    "prompt": "Write a poem about open source machine learning in the style of Byron.",
    "max_length": 500,
    "temperature": 1,
    "length_penalty": 1,
    "repetition_penalty": 1
  },
  "logs": "predict-timings173549: Starting prediction - 1936.54s since start, 16.07s since last log\nThe attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\nSetting `pad_token_id` to `eos_token_id`:11 for open-end generation.",
  "metrics": {
    "predict_time": 19.198896,
    "total_time": 19.128302
  },
  "output": [
    "Thy",
    " heart",
    " shall",
    " bloom",
    " like",
    " an",
    " open",
    " source",
    " flower,\nAnd",
    " like",
    " a",
    " machine,",
    " thine",
    " learning",
    " shall",
    " grow.\nThe",
    " seeds",
    " of",
    " a",
    " thousand",
    " algorithms,\nShall",
    " make",
    " thy",
    " understanding",
    " and",
    " skill",
    " ever",
    " glow.\nIn",
    " thy",
    " hand,",
    " wisdom",
    " shall",
    " grow",
    " like",
    " a",
    " tree,\nWith",
    " roots",
    " deep",
    " in",
    " the",
    " open",
    " source",
    " ground.\nThy",
    " knowledge",
    " as",
    " wide",
    " as",
    " the",
    " infinite",
    " sea,\nShall",
    " bring",
    " to",
    " thee",
    " power",
    " far",
    " beyond",
    " what",
    " is",
    " found.\nThou",
    " shalt",
    " become",
    " as",
    " masters",
    " of",
    " machine",
    " learning,\nWhose",
    " wisdom",
    " and",
    " skills",
    " shall",
    " surpass",
    " the",
    " greatest",
    " of",
    " minds.\nNo",
    " boundaries",
    " or",
    " limits",
    " shall",
    " thee",
    " be",
    " learning,\nBut",
    " thy",
    " heart",
    " shall",
    " be",
    " opened",
    " up",
    " to",
    " all",
    " that",
    " is",
    " kind.\nThen",
    " shall",
    " thy",
    " soul",
    " become",
    " a",
    " true",
    " machine,\nWith",
    " wisdom",
    " and",
    " knowledge",
    " beyond",
    " measure.\nThy",
    " work",
    " shall",
    " be",
    " done",
    " and",
    " thy",
    " goals",
    " shall",
    " be",
    " reached,\nUntil",
    " thou",
    " become",
    " true",
    " masters",
    " of",
    " open",
    " source",
    " and",
    " the",
    " machine."
  ],
  "started_at": "2023-07-07T20:34:39.417694Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2p2fdndbbkghrx2frxg5nvrltu",
    "cancel": "https://api.replicate.com/v1/predictions/2p2fdndbbkghrx2frxg5nvrltu/cancel"
  },
  "version": "7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c"
}

Generated in

19.2 seconds

Tweak it Iterate in playground Share Report

Prediction

joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c

Model

joehoover/falcon-40b-instruct:7eb0f4b1

6ydjisdbt6z4vbaffrcpmxcy5q

Status

Succeeded

Source

Web

Hardware

4x A100 (40GB)

Total duration

12.1s

Created

about 2 years ago

Input

seed: -1
top_p: 0.5
prompt: Briefly summarize this text: """ In artificial neural networks, attention is a technique that is meant to mimic cognitive attention. This effect enhances some parts of the input data while diminishing other parts—the motivation being that the network should devote more focus to the important parts of the data, even though they may be a small portion of an image or sentence. Learning which part of the data is more important than another depends on the context, and this is trained by gradient descent. Attention-like mechanisms were introduced in the 1990s under names like multiplicative modules, sigma pi units,[1] and hyper-networks.[2] The flexibility of these models comes from the introduction of "soft" weights that can change during runtime, in contrast to standard weights that must remain fixed at runtime. Uses of attention include memory in fast weight controllers,[3] neural Turing machines, reasoning tasks in differentiable neural computers,[4] language processing in transformers, and LSTMs, and multi-sensory data processing (sound, images, video, and text) in perceivers.[5][6][7][8]"""
max_length: 1000
temperature: 0.75
length_penalty: 1
repetition_penalty: 1

{
  "seed": -1,
  "top_p": 0.5,
  "prompt": "Briefly summarize this text: \n\n\"\"\"\nIn artificial neural networks, attention is a technique that is meant to mimic cognitive attention. This effect enhances some parts of the input data while diminishing other parts—the motivation being that the network should devote more focus to the important parts of the data, even though they may be a small portion of an image or sentence. Learning which part of the data is more important than another depends on the context, and this is trained by gradient descent.\n\nAttention-like mechanisms were introduced in the 1990s under names like multiplicative modules, sigma pi units,[1] and hyper-networks.[2] The flexibility of these models comes from the introduction of \"soft\" weights that can change during runtime, in contrast to standard weights that must remain fixed at runtime. Uses of attention include memory in fast weight controllers,[3] neural Turing machines, reasoning tasks in differentiable neural computers,[4] language processing in transformers, and LSTMs, and multi-sensory data processing (sound, images, video, and text) in perceivers.[5][6][7][8]\"\"\"\n",
  "max_length": 1000,
  "temperature": 0.75,
  "length_penalty": 1,
  "repetition_penalty": 1
}

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 joehoover/falcon-40b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
  {
    input: {
      seed: -1,
      top_p: 0.5,
      prompt: "Briefly summarize this text: \n\n\"\"\"\nIn artificial neural networks, attention is a technique that is meant to mimic cognitive attention. This effect enhances some parts of the input data while diminishing other parts—the motivation being that the network should devote more focus to the important parts of the data, even though they may be a small portion of an image or sentence. Learning which part of the data is more important than another depends on the context, and this is trained by gradient descent.\n\nAttention-like mechanisms were introduced in the 1990s under names like multiplicative modules, sigma pi units,[1] and hyper-networks.[2] The flexibility of these models comes from the introduction of \"soft\" weights that can change during runtime, in contrast to standard weights that must remain fixed at runtime. Uses of attention include memory in fast weight controllers,[3] neural Turing machines, reasoning tasks in differentiable neural computers,[4] language processing in transformers, and LSTMs, and multi-sensory data processing (sound, images, video, and text) in perceivers.[5][6][7][8]\"\"\"\n",
      max_length: 1000,
      temperature: 0.75,
      length_penalty: 1,
      repetition_penalty: 1
    }
  }
);

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 joehoover/falcon-40b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
    input={
        "seed": -1,
        "top_p": 0.5,
        "prompt": "Briefly summarize this text: \n\n\"\"\"\nIn artificial neural networks, attention is a technique that is meant to mimic cognitive attention. This effect enhances some parts of the input data while diminishing other parts—the motivation being that the network should devote more focus to the important parts of the data, even though they may be a small portion of an image or sentence. Learning which part of the data is more important than another depends on the context, and this is trained by gradient descent.\n\nAttention-like mechanisms were introduced in the 1990s under names like multiplicative modules, sigma pi units,[1] and hyper-networks.[2] The flexibility of these models comes from the introduction of \"soft\" weights that can change during runtime, in contrast to standard weights that must remain fixed at runtime. Uses of attention include memory in fast weight controllers,[3] neural Turing machines, reasoning tasks in differentiable neural computers,[4] language processing in transformers, and LSTMs, and multi-sensory data processing (sound, images, video, and text) in perceivers.[5][6][7][8]\"\"\"\n",
        "max_length": 1000,
        "temperature": 0.75,
        "length_penalty": 1,
        "repetition_penalty": 1
    }
)

# The joehoover/falcon-40b-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/joehoover/falcon-40b-instruct/api#output-schema
    print(item, end="")

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

Run joehoover/falcon-40b-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": "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
    "input": {
      "seed": -1,
      "top_p": 0.5,
      "prompt": "Briefly summarize this text: \\n\\n\\"\\"\\"\\nIn artificial neural networks, attention is a technique that is meant to mimic cognitive attention. This effect enhances some parts of the input data while diminishing other parts—the motivation being that the network should devote more focus to the important parts of the data, even though they may be a small portion of an image or sentence. Learning which part of the data is more important than another depends on the context, and this is trained by gradient descent.\\n\\nAttention-like mechanisms were introduced in the 1990s under names like multiplicative modules, sigma pi units,[1] and hyper-networks.[2] The flexibility of these models comes from the introduction of \\"soft\\" weights that can change during runtime, in contrast to standard weights that must remain fixed at runtime. Uses of attention include memory in fast weight controllers,[3] neural Turing machines, reasoning tasks in differentiable neural computers,[4] language processing in transformers, and LSTMs, and multi-sensory data processing (sound, images, video, and text) in perceivers.[5][6][7][8]\\"\\"\\"\\n",
      "max_length": 1000,
      "temperature": 0.75,
      "length_penalty": 1,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

This text summarizes the concept of attention in artificial neural networks, which is a technique that mimics cognitive attention. It enhances some parts of the input data while diminishing others, allowing the network to focus on the important parts of the data. The text also discusses the history of attention-like mechanisms in neural networks and their uses in various applications such as memory, reasoning, and language processing.

{
  "completed_at": "2023-07-08T18:58:55.574179Z",
  "created_at": "2023-07-08T18:58:43.517989Z",
  "data_removed": false,
  "error": null,
  "id": "6ydjisdbt6z4vbaffrcpmxcy5q",
  "input": {
    "seed": -1,
    "top_p": 0.5,
    "prompt": "Briefly summarize this text: \n\n\"\"\"\nIn artificial neural networks, attention is a technique that is meant to mimic cognitive attention. This effect enhances some parts of the input data while diminishing other parts—the motivation being that the network should devote more focus to the important parts of the data, even though they may be a small portion of an image or sentence. Learning which part of the data is more important than another depends on the context, and this is trained by gradient descent.\n\nAttention-like mechanisms were introduced in the 1990s under names like multiplicative modules, sigma pi units,[1] and hyper-networks.[2] The flexibility of these models comes from the introduction of \"soft\" weights that can change during runtime, in contrast to standard weights that must remain fixed at runtime. Uses of attention include memory in fast weight controllers,[3] neural Turing machines, reasoning tasks in differentiable neural computers,[4] language processing in transformers, and LSTMs, and multi-sensory data processing (sound, images, video, and text) in perceivers.[5][6][7][8]\"\"\"\n",
    "max_length": 1000,
    "temperature": 0.75,
    "length_penalty": 1,
    "repetition_penalty": 1
  },
  "logs": "predict-timings808875: Starting prediction - 1451.14s since start, 9.49s since last log\nThe attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\nSetting `pad_token_id` to `eos_token_id`:11 for open-end generation.",
  "metrics": {
    "predict_time": 12.062885,
    "total_time": 12.05619
  },
  "output": [
    "This",
    " text",
    " summarizes",
    " the",
    " concept",
    " of",
    " attention",
    " in",
    " artificial",
    " neural",
    " networks,",
    " which",
    " is",
    " a",
    " technique",
    " that",
    " mimics",
    " cognitive",
    " attention.",
    " It",
    " enhances",
    " some",
    " parts",
    " of",
    " the",
    " input",
    " data",
    " while",
    " diminishing",
    " others,",
    " allowing",
    " the",
    " network",
    " to",
    " focus",
    " on",
    " the",
    " important",
    " parts",
    " of",
    " the",
    " data.",
    " The",
    " text",
    " also",
    " discusses",
    " the",
    " history",
    " of",
    " attention-like",
    " mechanisms",
    " in",
    " neural",
    " networks",
    " and",
    " their",
    " uses",
    " in",
    " various",
    " applications",
    " such",
    " as",
    " memory,",
    " reasoning,",
    " and",
    " language",
    " processing."
  ],
  "started_at": "2023-07-08T18:58:43.511294Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6ydjisdbt6z4vbaffrcpmxcy5q",
    "cancel": "https://api.replicate.com/v1/predictions/6ydjisdbt6z4vbaffrcpmxcy5q/cancel"
  },
  "version": "7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c"
}

Generated in

12.1 seconds

Tweak it Iterate in playground Share Report

Prediction

joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c

Model

joehoover/falcon-40b-instruct:7eb0f4b1

5mg3fydbn456bl3uffjggrnsku

Status

Succeeded

Source

Web

Hardware

4x A100 (40GB)

Total duration

1m 45s

Created

about 2 years ago by @joehoover

Input

seed: -1
top_p: 1
prompt: You're a story outline writer. Given a description of a story, you produce a short, high-level outline that could be used to draft the story. Here's the description: The story is in the style of Edger Allan Poe. It is about strange lilac bush that seems to never lose it's flowers. The story makes readers feel uneasy and it has a surprising twist at the end. The story does not focus on the supernatural but, rather, builds tension through realism and by focusing on the dark side of human nature. Based on those details, write a short outline of this story's plot. Specify details like location, characters, and plot. Explain exactly what the surprising twist at the end is.
max_length: 1000
temperature: 0.9
length_penalty: 0.8
repetition_penalty: 1

{
  "seed": -1,
  "top_p": 1,
  "prompt": "You're a story outline writer. Given a description of a story, you produce a short, high-level outline that could be used to draft the story. Here's the description:\n\nThe story is in the style of Edger Allan Poe. It is about strange lilac bush that seems to never lose it's flowers. The story makes readers feel uneasy and it has a surprising twist at the end. The story does not focus on the supernatural but, rather, builds tension through realism and by focusing on the dark side of human nature.\n\nBased on those details, write a short outline of this story's plot. Specify details like location, characters, and plot. Explain exactly what the surprising twist at the end is. ",
  "max_length": 1000,
  "temperature": 0.9,
  "length_penalty": 0.8,
  "repetition_penalty": 1
}

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 joehoover/falcon-40b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
  {
    input: {
      seed: -1,
      top_p: 1,
      prompt: "You're a story outline writer. Given a description of a story, you produce a short, high-level outline that could be used to draft the story. Here's the description:\n\nThe story is in the style of Edger Allan Poe. It is about strange lilac bush that seems to never lose it's flowers. The story makes readers feel uneasy and it has a surprising twist at the end. The story does not focus on the supernatural but, rather, builds tension through realism and by focusing on the dark side of human nature.\n\nBased on those details, write a short outline of this story's plot. Specify details like location, characters, and plot. Explain exactly what the surprising twist at the end is. ",
      max_length: 1000,
      temperature: 0.9,
      length_penalty: 0.8,
      repetition_penalty: 1
    }
  }
);

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 joehoover/falcon-40b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
    input={
        "seed": -1,
        "top_p": 1,
        "prompt": "You're a story outline writer. Given a description of a story, you produce a short, high-level outline that could be used to draft the story. Here's the description:\n\nThe story is in the style of Edger Allan Poe. It is about strange lilac bush that seems to never lose it's flowers. The story makes readers feel uneasy and it has a surprising twist at the end. The story does not focus on the supernatural but, rather, builds tension through realism and by focusing on the dark side of human nature.\n\nBased on those details, write a short outline of this story's plot. Specify details like location, characters, and plot. Explain exactly what the surprising twist at the end is. ",
        "max_length": 1000,
        "temperature": 0.9,
        "length_penalty": 0.8,
        "repetition_penalty": 1
    }
)

# The joehoover/falcon-40b-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/joehoover/falcon-40b-instruct/api#output-schema
    print(item, end="")

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

Run joehoover/falcon-40b-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": "joehoover/falcon-40b-instruct:7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c",
    "input": {
      "seed": -1,
      "top_p": 1,
      "prompt": "You\'re a story outline writer. Given a description of a story, you produce a short, high-level outline that could be used to draft the story. Here\'s the description:\\n\\nThe story is in the style of Edger Allan Poe. It is about strange lilac bush that seems to never lose it\'s flowers. The story makes readers feel uneasy and it has a surprising twist at the end. The story does not focus on the supernatural but, rather, builds tension through realism and by focusing on the dark side of human nature.\\n\\nBased on those details, write a short outline of this story\'s plot. Specify details like location, characters, and plot. Explain exactly what the surprising twist at the end is. ",
      "max_length": 1000,
      "temperature": 0.9,
      "length_penalty": 0.8,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

THE LILAC BUSH INTRO: We see a secluded mansion, shrouded in mist, that appears to be a house out of time. A lone lilac bush is swaying violently in the wind. The only sound is the rustling of leaves as though something is hiding in them. ACT ONE: A man walks outside and is drawn to the lilac bush. He notices that it's been without new blossoms for weeks, but still, it remains vibrant and alive. He feels like something is off, as though he is being watched. He tries to shake off the feeling but is unable to. As he turns to walk back inside, a chill runs down his spine. ACT TWO: The man is unable to sleep that night. He can feel a sense of unease and sees shadows moving outside. He decides to investigate and goes to the window. What he sees makes his blood run cold: a woman with wild eyes and matted hair, staring at him from the shadows of the lilac bush. She whispers to him, "You don't know what you're dealing with." ACT THREE: The man goes to investigate the woman in the lilac bush. As he approaches, he sees that she has scratches on her arms and legs. She tells him that she got caught in the bushes and was attacked. He believes her and tries to help her, but she warns him again, "You don't know what you're dealing with." ACT FOUR: The man goes back to his mansion and tries to forget about the lilac bush and the woman. But each night, the woman visits him in his dreams, taunting him and whispering that he doesn't know what he's dealing with. The man is slowly driven insane by the visions and starts to see the world in a different light. THE TWIST: The man is driven to chop down the lilac bush. As he is chopping, he notices that the leaves are moving, and as he looks up, he sees the face of the woman emerge from within the bush. The woman screams, "You're right. You don't know what you're dealing with. I am the lilac bush." And as the man's blood runs cold, we flashback to the beginning and see that she was the dead wife of the man who owned the mansion before. She was murdered and then buried beneath the lilac bush. Her ghost has possessed the lilac bush and wants revenge. END.

{
  "completed_at": "2023-07-08T19:18:06.295870Z",
  "created_at": "2023-07-08T19:16:21.686539Z",
  "data_removed": false,
  "error": null,
  "id": "5mg3fydbn456bl3uffjggrnsku",
  "input": {
    "seed": -1,
    "top_p": 1,
    "prompt": "You're a story outline writer. Given a description of a story, you produce a short, high-level outline that could be used to draft the story. Here's the description:\n\nThe story is in the style of Edger Allan Poe. It is about strange lilac bush that seems to never lose it's flowers. The story makes readers feel uneasy and it has a surprising twist at the end. The story does not focus on the supernatural but, rather, builds tension through realism and by focusing on the dark side of human nature.\n\nBased on those details, write a short outline of this story's plot. Specify details like location, characters, and plot. Explain exactly what the surprising twist at the end is. ",
    "max_length": 1000,
    "temperature": 0.9,
    "length_penalty": 0.8,
    "repetition_penalty": 1
  },
  "logs": "predict-timings808875: Starting prediction - 2509.31s since start, 123.31s since last log\nThe attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\nSetting `pad_token_id` to `eos_token_id`:11 for open-end generation.",
  "metrics": {
    "predict_time": 104.612017,
    "total_time": 104.609331
  },
  "output": [
    "THE",
    " LILAC",
    " BUSH\n\nINTRO:",
    " We",
    " see",
    " a",
    " secluded",
    " mansion,",
    " shrouded",
    " in",
    " mist,",
    " that",
    " appears",
    " to",
    " be",
    " a",
    " house",
    " out",
    " of",
    " time.",
    " A",
    " lone",
    " lilac",
    " bush",
    " is",
    " swaying",
    " violently",
    " in",
    " the",
    " wind.",
    " The",
    " only",
    " sound",
    " is",
    " the",
    " rustling",
    " of",
    " leaves",
    " as",
    " though",
    " something",
    " is",
    " hiding",
    " in",
    " them.\n\nACT",
    " ONE:",
    " A",
    " man",
    " walks",
    " outside",
    " and",
    " is",
    " drawn",
    " to",
    " the",
    " lilac",
    " bush.",
    " He",
    " notices",
    " that",
    " it's",
    " been",
    " without",
    " new",
    " blossoms",
    " for",
    " weeks,",
    " but",
    " still,",
    " it",
    " remains",
    " vibrant",
    " and",
    " alive.",
    " He",
    " feels",
    " like",
    " something",
    " is",
    " off,",
    " as",
    " though",
    " he",
    " is",
    " being",
    " watched.",
    " He",
    " tries",
    " to",
    " shake",
    " off",
    " the",
    " feeling",
    " but",
    " is",
    " unable",
    " to.",
    " As",
    " he",
    " turns",
    " to",
    " walk",
    " back",
    " inside,",
    " a",
    " chill",
    " runs",
    " down",
    " his",
    " spine.\n\nACT",
    " TWO:",
    " The",
    " man",
    " is",
    " unable",
    " to",
    " sleep",
    " that",
    " night.",
    " He",
    " can",
    " feel",
    " a",
    " sense",
    " of",
    " unease",
    " and",
    " sees",
    " shadows",
    " moving",
    " outside.",
    " He",
    " decides",
    " to",
    " investigate",
    " and",
    " goes",
    " to",
    " the",
    " window.",
    " What",
    " he",
    " sees",
    " makes",
    " his",
    " blood",
    " run",
    " cold:",
    " a",
    " woman",
    " with",
    " wild",
    " eyes",
    " and",
    " matted",
    " hair,",
    " staring",
    " at",
    " him",
    " from",
    " the",
    " shadows",
    " of",
    " the",
    " lilac",
    " bush.",
    " She",
    " whispers",
    " to",
    " him,",
    " \"You",
    " don't",
    " know",
    " what",
    " you're",
    " dealing",
    " with.\"\n\nACT",
    " THREE:",
    " The",
    " man",
    " goes",
    " to",
    " investigate",
    " the",
    " woman",
    " in",
    " the",
    " lilac",
    " bush.",
    " As",
    " he",
    " approaches,",
    " he",
    " sees",
    " that",
    " she",
    " has",
    " scratches",
    " on",
    " her",
    " arms",
    " and",
    " legs.",
    " She",
    " tells",
    " him",
    " that",
    " she",
    " got",
    " caught",
    " in",
    " the",
    " bushes",
    " and",
    " was",
    " attacked.",
    " He",
    " believes",
    " her",
    " and",
    " tries",
    " to",
    " help",
    " her,",
    " but",
    " she",
    " warns",
    " him",
    " again,",
    " \"You",
    " don't",
    " know",
    " what",
    " you're",
    " dealing",
    " with.\"\n\nACT",
    " FOUR:",
    " The",
    " man",
    " goes",
    " back",
    " to",
    " his",
    " mansion",
    " and",
    " tries",
    " to",
    " forget",
    " about",
    " the",
    " lilac",
    " bush",
    " and",
    " the",
    " woman.",
    " But",
    " each",
    " night,",
    " the",
    " woman",
    " visits",
    " him",
    " in",
    " his",
    " dreams,",
    " taunting",
    " him",
    " and",
    " whispering",
    " that",
    " he",
    " doesn't",
    " know",
    " what",
    " he's",
    " dealing",
    " with.",
    " The",
    " man",
    " is",
    " slowly",
    " driven",
    " insane",
    " by",
    " the",
    " visions",
    " and",
    " starts",
    " to",
    " see",
    " the",
    " world",
    " in",
    " a",
    " different",
    " light.\n\nTHE",
    " TWIST:",
    " The",
    " man",
    " is",
    " driven",
    " to",
    " chop",
    " down",
    " the",
    " lilac",
    " bush.",
    " As",
    " he",
    " is",
    " chopping,",
    " he",
    " notices",
    " that",
    " the",
    " leaves",
    " are",
    " moving,",
    " and",
    " as",
    " he",
    " looks",
    " up,",
    " he",
    " sees",
    " the",
    " face",
    " of",
    " the",
    " woman",
    " emerge",
    " from",
    " within",
    " the",
    " bush.",
    " The",
    " woman",
    " screams,",
    " \"You're",
    " right.",
    " You",
    " don't",
    " know",
    " what",
    " you're",
    " dealing",
    " with.",
    " I",
    " am",
    " the",
    " lilac",
    " bush.\"",
    " And",
    " as",
    " the",
    " man's",
    " blood",
    " runs",
    " cold,",
    " we",
    " flashback",
    " to",
    " the",
    " beginning",
    " and",
    " see",
    " that",
    " she",
    " was",
    " the",
    " dead",
    " wife",
    " of",
    " the",
    " man",
    " who",
    " owned",
    " the",
    " mansion",
    " before.",
    " She",
    " was",
    " murdered",
    " and",
    " then",
    " buried",
    " beneath",
    " the",
    " lilac",
    " bush.",
    " Her",
    " ghost",
    " has",
    " possessed",
    " the",
    " lilac",
    " bush",
    " and",
    " wants",
    " revenge.\n\nEND."
  ],
  "started_at": "2023-07-08T19:16:21.683853Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5mg3fydbn456bl3uffjggrnsku",
    "cancel": "https://api.replicate.com/v1/predictions/5mg3fydbn456bl3uffjggrnsku/cancel"
  },
  "version": "7eb0f4b1ff770ab4f68c3a309dd4984469749b7323a3d47fd2d5e09d58836d3c"
}

Generated in

1 minute 45 seconds

Tweak it Iterate in playground Share Report

Want to make some of these yourself?

Run this model

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (2p2fdndbbkghrx2frxg5nvrltu)

Logs (6ydjisdbt6z4vbaffrcpmxcy5q)

Logs (5mg3fydbn456bl3uffjggrnsku)