adirik / mamba-1.4b

Base version of Mamba 1.4B, a 1.4 billion parameter state space language model

Cold

Public
104 runs
L40S
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d

Model

adirik/mamba-1.4b:917b6c8e

fimoyblbwx2ze6myg6nhrkwpwy

Status

Succeeded

Source

Web

Hardware

A40

Total duration

1m 40s

Created

over 1 year ago

Input

top_k: 1
top_p: 1
prompt: How are you doing today?
max_length: 100
temperature: 1
repetition_penalty: 1.2

{
  "top_k": 1,
  "top_p": 1,
  "prompt": "How are you doing today?",
  "max_length": 100,
  "temperature": 1,
  "repetition_penalty": 1.2
}

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 adirik/mamba-1.4b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d",
  {
    input: {
      top_k: 1,
      top_p: 1,
      prompt: "How are you doing today?",
      max_length: 100,
      temperature: 1,
      repetition_penalty: 1.2
    }
  }
);

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 adirik/mamba-1.4b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d",
    input={
        "top_k": 1,
        "top_p": 1,
        "prompt": "How are you doing today?",
        "max_length": 100,
        "temperature": 1,
        "repetition_penalty": 1.2
    }
)

# The adirik/mamba-1.4b 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/adirik/mamba-1.4b/api#output-schema
    print(item, end="")

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

Run adirik/mamba-1.4b 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": "adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d",
    "input": {
      "top_k": 1,
      "top_p": 1,
      "prompt": "How are you doing today?",
      "max_length": 100,
      "temperature": 1,
      "repetition_penalty": 1.2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

I'm fine. I'm just a little bit tired, but other than that... What's the matter with your leg? Nothing. It was nothing. Just some minor injuries from last night. You're not hurt at all? No bruises or anything like this? No. Nothing. And how about your back? Is it okay there too now? Yes! Yesterday we were in the car and I fell down on my knees and then I got up again

{
  "completed_at": "2024-02-05T18:23:44.839149Z",
  "created_at": "2024-02-05T18:22:04.426100Z",
  "data_removed": false,
  "error": null,
  "id": "fimoyblbwx2ze6myg6nhrkwpwy",
  "input": {
    "top_k": 1,
    "top_p": 1,
    "prompt": "How are you doing today?",
    "max_length": 100,
    "temperature": 1,
    "repetition_penalty": 1.2
  },
  "logs": null,
  "metrics": {
    "predict_time": 8.551045,
    "total_time": 100.413049
  },
  "output": [
    "\n",
    "",
    "",
    "I'm ",
    "",
    "fine. ",
    "",
    "I'm ",
    "just ",
    "a ",
    "little ",
    "bit ",
    "",
    "tired, ",
    "but ",
    "other ",
    "than ",
    "",
    "that...\n",
    "",
    "",
    "What's ",
    "the ",
    "matter ",
    "with ",
    "your ",
    "",
    "leg?\n",
    "",
    "",
    "Nothing. ",
    "It ",
    "was ",
    "",
    "nothing. ",
    "Just ",
    "some ",
    "minor ",
    "injuries ",
    "from ",
    "last ",
    "",
    "night.\n",
    "",
    "",
    "You're ",
    "not ",
    "hurt ",
    "at ",
    "",
    "all? ",
    "No ",
    "",
    "bruises ",
    "or ",
    "anything ",
    "like ",
    "",
    "this?\n",
    "",
    "",
    "No. ",
    "",
    "Nothing.\n",
    "",
    "And ",
    "how ",
    "about ",
    "your ",
    "",
    "back? ",
    "Is ",
    "it ",
    "okay ",
    "there ",
    "too ",
    "",
    "now?\n",
    "",
    "",
    "Yes! ",
    "",
    "Yesterday ",
    "we ",
    "were ",
    "in ",
    "the ",
    "car ",
    "and ",
    "I ",
    "fell ",
    "down ",
    "on ",
    "my ",
    "knees ",
    "and ",
    "then ",
    "I ",
    "got ",
    "up ",
    "again"
  ],
  "started_at": "2024-02-05T18:23:36.288104Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/kkm2mm53c6tgae73mhf3y5a5kjik3spcjieeijm3fgqwv4f2rh7q",
    "get": "https://api.replicate.com/v1/predictions/fimoyblbwx2ze6myg6nhrkwpwy",
    "cancel": "https://api.replicate.com/v1/predictions/fimoyblbwx2ze6myg6nhrkwpwy/cancel"
  },
  "version": "917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d"
}

Generated in

8.6 seconds

Tweak it Share Report

Prediction

adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d

Model

adirik/mamba-1.4b:917b6c8e

fimoyblbwx2ze6myg6nhrkwpwy

Status

Succeeded

Source

Web

Hardware

A40

Total duration

1m 40s

Created

over 1 year ago

Input

top_k: 1
top_p: 1
prompt: How are you doing today?
max_length: 100
temperature: 1
repetition_penalty: 1.2

{
  "top_k": 1,
  "top_p": 1,
  "prompt": "How are you doing today?",
  "max_length": 100,
  "temperature": 1,
  "repetition_penalty": 1.2
}

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 adirik/mamba-1.4b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d",
  {
    input: {
      top_k: 1,
      top_p: 1,
      prompt: "How are you doing today?",
      max_length: 100,
      temperature: 1,
      repetition_penalty: 1.2
    }
  }
);

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 adirik/mamba-1.4b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d",
    input={
        "top_k": 1,
        "top_p": 1,
        "prompt": "How are you doing today?",
        "max_length": 100,
        "temperature": 1,
        "repetition_penalty": 1.2
    }
)

# The adirik/mamba-1.4b 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/adirik/mamba-1.4b/api#output-schema
    print(item, end="")

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

Run adirik/mamba-1.4b 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": "adirik/mamba-1.4b:917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d",
    "input": {
      "top_k": 1,
      "top_p": 1,
      "prompt": "How are you doing today?",
      "max_length": 100,
      "temperature": 1,
      "repetition_penalty": 1.2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-02-05T18:23:44.839149Z",
  "created_at": "2024-02-05T18:22:04.426100Z",
  "data_removed": false,
  "error": null,
  "id": "fimoyblbwx2ze6myg6nhrkwpwy",
  "input": {
    "top_k": 1,
    "top_p": 1,
    "prompt": "How are you doing today?",
    "max_length": 100,
    "temperature": 1,
    "repetition_penalty": 1.2
  },
  "logs": null,
  "metrics": {
    "predict_time": 8.551045,
    "total_time": 100.413049
  },
  "output": [
    "\n",
    "",
    "",
    "I'm ",
    "",
    "fine. ",
    "",
    "I'm ",
    "just ",
    "a ",
    "little ",
    "bit ",
    "",
    "tired, ",
    "but ",
    "other ",
    "than ",
    "",
    "that...\n",
    "",
    "",
    "What's ",
    "the ",
    "matter ",
    "with ",
    "your ",
    "",
    "leg?\n",
    "",
    "",
    "Nothing. ",
    "It ",
    "was ",
    "",
    "nothing. ",
    "Just ",
    "some ",
    "minor ",
    "injuries ",
    "from ",
    "last ",
    "",
    "night.\n",
    "",
    "",
    "You're ",
    "not ",
    "hurt ",
    "at ",
    "",
    "all? ",
    "No ",
    "",
    "bruises ",
    "or ",
    "anything ",
    "like ",
    "",
    "this?\n",
    "",
    "",
    "No. ",
    "",
    "Nothing.\n",
    "",
    "And ",
    "how ",
    "about ",
    "your ",
    "",
    "back? ",
    "Is ",
    "it ",
    "okay ",
    "there ",
    "too ",
    "",
    "now?\n",
    "",
    "",
    "Yes! ",
    "",
    "Yesterday ",
    "we ",
    "were ",
    "in ",
    "the ",
    "car ",
    "and ",
    "I ",
    "fell ",
    "down ",
    "on ",
    "my ",
    "knees ",
    "and ",
    "then ",
    "I ",
    "got ",
    "up ",
    "again"
  ],
  "started_at": "2024-02-05T18:23:36.288104Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/kkm2mm53c6tgae73mhf3y5a5kjik3spcjieeijm3fgqwv4f2rh7q",
    "get": "https://api.replicate.com/v1/predictions/fimoyblbwx2ze6myg6nhrkwpwy",
    "cancel": "https://api.replicate.com/v1/predictions/fimoyblbwx2ze6myg6nhrkwpwy/cancel"
  },
  "version": "917b6c8e21c963b41147b2f232f8e5f3c2f572e54f63897ed5dc6793a9972f5d"
}

Generated in

8.6 seconds

Tweak it Share Report