fofr / neuromancer-13b

debug
top_k: 500
top_p: 0.9
prompt: Given the following input, rewrite it in the style of neuromancer: [INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT] [OUTPUT]
temperature: 0.75
max_new_tokens: 1000
min_new_tokens: 256
stop_sequences: [/OUTPUT]

{
  "debug": false,
  "top_k": 500,
  "top_p": 0.9,
  "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\n[OUTPUT] ",
  "temperature": 0.75,
  "max_new_tokens": 1000,
  "min_new_tokens": 256,
  "stop_sequences": "[/OUTPUT]"
}

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 fofr/neuromancer-13b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/neuromancer-13b:cb659be290cf781122b8d3abfb5ae957c798035b679a09ad5c0ae8ce6023445a",
  {
    input: {
      debug: false,
      top_k: 500,
      top_p: 0.9,
      prompt: "Given the following input, rewrite it in the style of neuromancer:\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\n[OUTPUT] ",
      temperature: 0.75,
      max_new_tokens: 1000,
      min_new_tokens: 256,
      stop_sequences: "[/OUTPUT]"
    }
  }
);

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 fofr/neuromancer-13b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/neuromancer-13b:cb659be290cf781122b8d3abfb5ae957c798035b679a09ad5c0ae8ce6023445a",
    input={
        "debug": False,
        "top_k": 500,
        "top_p": 0.9,
        "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\n[OUTPUT] ",
        "temperature": 0.75,
        "max_new_tokens": 1000,
        "min_new_tokens": 256,
        "stop_sequences": "[/OUTPUT]"
    }
)

# The fofr/neuromancer-13b 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/fofr/neuromancer-13b/api#output-schema
    print(item, end="")

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

Run fofr/neuromancer-13b 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": "fofr/neuromancer-13b:cb659be290cf781122b8d3abfb5ae957c798035b679a09ad5c0ae8ce6023445a",
    "input": {
      "debug": false,
      "top_k": 500,
      "top_p": 0.9,
      "prompt": "Given the following input, rewrite it in the style of neuromancer:\\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\\n[OUTPUT] ",
      "temperature": 0.75,
      "max_new_tokens": 1000,
      "min_new_tokens": 256,
      "stop_sequences": "[/OUTPUT]"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/fofr/neuromancer-13b@sha256:cb659be290cf781122b8d3abfb5ae957c798035b679a09ad5c0ae8ce6023445a \
  -i 'debug=false' \
  -i 'top_k=500' \
  -i 'top_p=0.9' \
  -i $'prompt="Given the following input, rewrite it in the style of neuromancer:\\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\\n[OUTPUT] "' \
  -i 'temperature=0.75' \
  -i 'max_new_tokens=1000' \
  -i 'min_new_tokens=256' \
  -i 'stop_sequences="[/OUTPUT]"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/fofr/neuromancer-13b@sha256:cb659be290cf781122b8d3abfb5ae957c798035b679a09ad5c0ae8ce6023445a
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "debug": false,
      "top_k": 500,
      "top_p": 0.9,
      "prompt": "Given the following input, rewrite it in the style of neuromancer:\\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\\n[OUTPUT] ",
      "temperature": 0.75,
      "max_new_tokens": 1000,
      "min_new_tokens": 256,
      "stop_sequences": "[/OUTPUT]"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

John ran as fast as he could toward the wild pikachu. He needed to capture it and bring it back to his trainer, Ash Ketchum. The moment he caught up with it, he realized that he was too late. It had already evolved into Raichu! With a burst of electricity, it knocked him out cold...

{
  "completed_at": "2023-09-13T07:03:17.274742Z",
  "created_at": "2023-09-13T07:03:14.416169Z",
  "data_removed": false,
  "error": null,
  "id": "lfij2w3byp5jyuloh32fma3rum",
  "input": {
    "debug": false,
    "top_k": 500,
    "top_p": 0.9,
    "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\n[OUTPUT] ",
    "temperature": 0.75,
    "max_new_tokens": 1000,
    "min_new_tokens": 256,
    "stop_sequences": "[/OUTPUT]"
  },
  "logs": "Your formatted prompt is:\nGiven the following input, rewrite it in the style of neuromancer:\n[INPUT] John needs to catch Pikachu to prove himself, a battle commences. [/INPUT]\n[OUTPUT]\nprevious weights were https://pbxt.replicate.delivery/FeDWbf765fPfDTzmQCCSFbKMdfUOPej8QZa6L8Z4b6B6Pn3YE/training_output.zip, switching to https://pbxt.replicate.delivery/j2aWHPtxmAr5Id2lmUFDeKK3iE7x2yp2QgDJm8aIHqc8a4xIA/training_output.zip\nOverall initialize_peft took 0.0001\nhostname: model-hs-f65583d2-ad5558a4ca97250e-gpu-a40-594759b748-4fm2g",
  "metrics": {
    "predict_time": 1.781942,
    "total_time": 2.858573
  },
  "output": [
    " John",
    " ran",
    " as",
    " fast",
    " as",
    " he",
    " could",
    " toward",
    " the",
    " wild",
    " p",
    "ik",
    "ach",
    "u",
    ".",
    " He",
    " needed",
    " to",
    " capture",
    " it",
    " and",
    " bring",
    " it",
    " back",
    " to",
    " his",
    " tra",
    "iner",
    ",",
    " Ash",
    " K",
    "etch",
    "um",
    ".",
    " The",
    " moment",
    " he",
    " caught",
    " up",
    " with",
    " it",
    ",",
    " he",
    " realized",
    " that",
    " he",
    " was",
    " too",
    " late",
    ".",
    " It",
    " had",
    " already",
    " evol",
    "ved",
    " into",
    " Ra",
    "ich",
    "u",
    "!",
    " With",
    " a",
    " burst",
    " of",
    " electric",
    "ity",
    ",",
    " it",
    " knock",
    "ed",
    " him",
    " out",
    " cold",
    "...",
    " "
  ],
  "started_at": "2023-09-13T07:03:15.492800Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/lfij2w3byp5jyuloh32fma3rum",
    "cancel": "https://api.replicate.com/v1/predictions/lfij2w3byp5jyuloh32fma3rum/cancel"
  },
  "version": "cb659be290cf781122b8d3abfb5ae957c798035b679a09ad5c0ae8ce6023445a"
}

Generated in

1.8 seconds

Tweak it Share Report

Prediction

fofr/neuromancer-13b:e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58

Model

fofr/neuromancer-13b:e8f6fe03

mdcki6tbe7n2tv6sfpmyrk5y34

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

8.2s

Created

almost 2 years ago

Input

debug
top_k: 55
top_p: 0.9
prompt: Given the following input, rewrite it in the style of neuromancer: [TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE] [NEUROMANCED]
temperature: 0.75
max_new_tokens: 1000
min_new_tokens: 100
stop_sequences: [/NEUROMANCED]

{
  "debug": false,
  "top_k": 55,
  "top_p": 0.9,
  "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\n[NEUROMANCED] ",
  "temperature": 0.75,
  "max_new_tokens": 1000,
  "min_new_tokens": 100,
  "stop_sequences": "[/NEUROMANCED]"
}

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 fofr/neuromancer-13b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/neuromancer-13b:e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58",
  {
    input: {
      debug: false,
      top_k: 55,
      top_p: 0.9,
      prompt: "Given the following input, rewrite it in the style of neuromancer:\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\n[NEUROMANCED] ",
      temperature: 0.75,
      max_new_tokens: 1000,
      min_new_tokens: 100,
      stop_sequences: "[/NEUROMANCED]"
    }
  }
);

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 fofr/neuromancer-13b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/neuromancer-13b:e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58",
    input={
        "debug": False,
        "top_k": 55,
        "top_p": 0.9,
        "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\n[NEUROMANCED] ",
        "temperature": 0.75,
        "max_new_tokens": 1000,
        "min_new_tokens": 100,
        "stop_sequences": "[/NEUROMANCED]"
    }
)

# The fofr/neuromancer-13b 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/fofr/neuromancer-13b/api#output-schema
    print(item, end="")

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

Run fofr/neuromancer-13b 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": "fofr/neuromancer-13b:e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58",
    "input": {
      "debug": false,
      "top_k": 55,
      "top_p": 0.9,
      "prompt": "Given the following input, rewrite it in the style of neuromancer:\\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\\n[NEUROMANCED] ",
      "temperature": 0.75,
      "max_new_tokens": 1000,
      "min_new_tokens": 100,
      "stop_sequences": "[/NEUROMANCED]"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/fofr/neuromancer-13b@sha256:e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58 \
  -i 'debug=false' \
  -i 'top_k=55' \
  -i 'top_p=0.9' \
  -i $'prompt="Given the following input, rewrite it in the style of neuromancer:\\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\\n[NEUROMANCED] "' \
  -i 'temperature=0.75' \
  -i 'max_new_tokens=1000' \
  -i 'min_new_tokens=100' \
  -i 'stop_sequences="[/NEUROMANCED]"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/fofr/neuromancer-13b@sha256:e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "debug": false,
      "top_k": 55,
      "top_p": 0.9,
      "prompt": "Given the following input, rewrite it in the style of neuromancer:\\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\\n[NEUROMANCED] ",
      "temperature": 0.75,
      "max_new_tokens": 1000,
      "min_new_tokens": 100,
      "stop_sequences": "[/NEUROMANCED]"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

John needed caffeine. He could have had a cup of tea or even black coffee, but he wanted that stimulant that made him feel like his brain was parting from his skull with a sucking sound as it expanded and grew sharper than any surgeon's knife. The cold liquid hit his stomach like an icepick, sending waves of nausea through his body. A smile crossed his face.

{
  "completed_at": "2023-09-13T10:47:41.437422Z",
  "created_at": "2023-09-13T10:47:33.220289Z",
  "data_removed": false,
  "error": null,
  "id": "mdcki6tbe7n2tv6sfpmyrk5y34",
  "input": {
    "debug": false,
    "top_k": 55,
    "top_p": 0.9,
    "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\n[NEUROMANCED] ",
    "temperature": 0.75,
    "max_new_tokens": 1000,
    "min_new_tokens": 100,
    "stop_sequences": "[/NEUROMANCED]"
  },
  "logs": null,
  "metrics": {
    "predict_time": 2.274779,
    "total_time": 8.217133
  },
  "output": [
    " John",
    " needed",
    " c",
    "aff",
    "e",
    "ine",
    ".",
    " He",
    " could",
    " have",
    " had",
    " a",
    " cup",
    " of",
    " tea",
    " or",
    " even",
    " black",
    " coffee",
    ",",
    " but",
    " he",
    " wanted",
    " that",
    " stim",
    "ul",
    "ant",
    " that",
    " made",
    " him",
    " feel",
    " like",
    " his",
    " brain",
    " was",
    " part",
    "ing",
    " from",
    " his",
    " sk",
    "ull",
    " with",
    " a",
    " su",
    "ck",
    "ing",
    " sound",
    " as",
    " it",
    " expanded",
    " and",
    " grew",
    " sh",
    "ar",
    "per",
    " than",
    " any",
    " sur",
    "geon",
    "'",
    "s",
    " kn",
    "ife",
    ".",
    " The",
    " cold",
    " liquid",
    " hit",
    " his",
    " st",
    "om",
    "ach",
    " like",
    " an",
    " ice",
    "pick",
    ",",
    " sending",
    " waves",
    " of",
    " n",
    "ause",
    "a",
    " through",
    " his",
    " body",
    ".",
    " A",
    " smile",
    " crossed",
    " his",
    " face",
    ".",
    " "
  ],
  "started_at": "2023-09-13T10:47:39.162643Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/mdcki6tbe7n2tv6sfpmyrk5y34",
    "cancel": "https://api.replicate.com/v1/predictions/mdcki6tbe7n2tv6sfpmyrk5y34/cancel"
  },
  "version": "e8f6fe03615d2ed962f4859d1d55e4d5497ddb357c6cb354f18b8de450cbee58"
}

Generated in

2.3 seconds

Tweak it Share Report