adirik / mamba-2.8b

Base version of Mamba 2.8B, a 2.8 billion parameter state space language model

Cold

Public
833 runs
L40S
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

adirik/mamba-2.8b:864ed9237f28ff2e8eb55ffc07e9f0d7857888cacb9c32a92081f24f49a861db

Model

adirik/mamba-2.8b:864ed923

m2mq75dbg5gfuvrtj2hiptbffa

Status

Succeeded

Source

Web

Hardware

A40

Total duration

12m 16s

Created

over 1 year ago

Input

top_k: 1
top_p: 1
prompt: How have you been doing lately?
max_length: 100
temperature: 1
repetition_penalty: 1.2

{
  "top_k": 1,
  "top_p": 1,
  "prompt": "How have you been doing lately?",
  "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-2.8b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/mamba-2.8b:864ed9237f28ff2e8eb55ffc07e9f0d7857888cacb9c32a92081f24f49a861db",
  {
    input: {
      top_k: 1,
      top_p: 1,
      prompt: "How have you been doing lately?",
      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-2.8b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/mamba-2.8b:864ed9237f28ff2e8eb55ffc07e9f0d7857888cacb9c32a92081f24f49a861db",
    input={
        "top_k": 1,
        "top_p": 1,
        "prompt": "How have you been doing lately?",
        "max_length": 100,
        "temperature": 1,
        "repetition_penalty": 1.2
    }
)

# The adirik/mamba-2.8b 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-2.8b/api#output-schema
    print(item, end="")

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

Run adirik/mamba-2.8b 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-2.8b:864ed9237f28ff2e8eb55ffc07e9f0d7857888cacb9c32a92081f24f49a861db",
    "input": {
      "top_k": 1,
      "top_p": 1,
      "prompt": "How have you been doing lately?",
      "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've had a lot of work to do, but it's all done now and that makes me happy! :) What are your plans for the future (in terms career-wise)? Are there any projects or things in particular on which we can expect more from you soon/soonish? Well... my plan is just keep working hard at what i am already good with: 3D modeling & animation etc.. And maybe try some other stuff like game development

{
  "completed_at": "2024-02-05T18:32:44.571760Z",
  "created_at": "2024-02-05T18:20:28.086361Z",
  "data_removed": false,
  "error": null,
  "id": "m2mq75dbg5gfuvrtj2hiptbffa",
  "input": {
    "top_k": 1,
    "top_p": 1,
    "prompt": "How have you been doing lately?",
    "max_length": 100,
    "temperature": 1,
    "repetition_penalty": 1.2
  },
  "logs": null,
  "metrics": {
    "predict_time": 6.855376,
    "total_time": 736.485399
  },
  "output": [
    "\n",
    "",
    "",
    "I'm ",
    "",
    "fine. ",
    "",
    "I've ",
    "had ",
    "a ",
    "lot ",
    "of ",
    "work ",
    "to ",
    "",
    "do, ",
    "but ",
    "",
    "it's ",
    "all ",
    "done ",
    "now ",
    "and ",
    "that ",
    "makes ",
    "me ",
    "",
    "happy! ",
    ":) ",
    "\n",
    "",
    "What ",
    "are ",
    "your ",
    "plans ",
    "for ",
    "the ",
    "future ",
    "",
    "(in ",
    "terms ",
    "",
    "",
    "",
    "career-wise)? ",
    "Are ",
    "there ",
    "any ",
    "projects ",
    "or ",
    "things ",
    "in ",
    "particular ",
    "on ",
    "which ",
    "we ",
    "can ",
    "expect ",
    "more ",
    "from ",
    "you ",
    "",
    "",
    "",
    "",
    "soon/soonish? \n",
    "  ",
    "",
    "",
    "Well... ",
    "my ",
    "plan ",
    "is ",
    "just ",
    "keep ",
    "working ",
    "hard ",
    "at ",
    "what ",
    "i ",
    "am ",
    "already ",
    "good ",
    "",
    "with: ",
    "",
    "3D ",
    "modeling ",
    "& ",
    "animation ",
    "",
    "etc.. ",
    "And ",
    "maybe ",
    "try ",
    "some ",
    "other ",
    "stuff ",
    "like ",
    "game ",
    "development"
  ],
  "started_at": "2024-02-05T18:32:37.716384Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/di65mue4feyvv7kgu4dwehvuds7fh6g6ze6dsnybbwozblyo4m3q",
    "get": "https://api.replicate.com/v1/predictions/m2mq75dbg5gfuvrtj2hiptbffa",
    "cancel": "https://api.replicate.com/v1/predictions/m2mq75dbg5gfuvrtj2hiptbffa/cancel"
  },
  "version": "864ed9237f28ff2e8eb55ffc07e9f0d7857888cacb9c32a92081f24f49a861db"
}

Generated in

6.9 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model