ydideh810 / cosmo-speak

A chat-bot that specialises in Space/Aeronautics knowledge.

Cold

Public
17 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

How do Sun and Earth sensors boost spacecraft navigation and mission success?How do Sun and Earth sensors boost spacecraft navigation and mission success?

Prompt to send to the model.

max_new_tokens

integer

(minimum: 1)

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 128

min_new_tokens

integer

(minimum: -1)

Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.

Default: -1

temperature

number

(minimum: 0.01, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.75

top_p

number

(minimum: 0, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 0.9

top_k

integer

(minimum: 0)

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens

Default: 50

stop_sequences

string

Shift + Return to add a new line

A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.

seed

integer

Random seed. Leave blank to randomize the seed

debug

boolean

provide debugging output in logs

Default: false

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

npx create-replicate --model=ydideh810/cosmo-speak

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 ydideh810/cosmo-speak using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "ydideh810/cosmo-speak:fd8ed7161c14133273cfa8fdc60a10143a0107a7d4adeb495ba98f22257d965e",
  {
    input: {
      debug: false,
      top_k: 50,
      top_p: 0.9,
      prompt: "How do Sun and Earth sensors boost spacecraft navigation and mission success?",
      temperature: 0.75,
      max_new_tokens: 128,
      min_new_tokens: -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

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 ydideh810/cosmo-speak using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "ydideh810/cosmo-speak:fd8ed7161c14133273cfa8fdc60a10143a0107a7d4adeb495ba98f22257d965e",
    input={
        "debug": False,
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "How do Sun and Earth sensors boost spacecraft navigation and mission success?",
        "temperature": 0.75,
        "max_new_tokens": 128,
        "min_new_tokens": -1
    }
)

# The ydideh810/cosmo-speak 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/ydideh810/cosmo-speak/api#output-schema
    print(item, end="")

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 ydideh810/cosmo-speak 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": "ydideh810/cosmo-speak:fd8ed7161c14133273cfa8fdc60a10143a0107a7d4adeb495ba98f22257d965e",
    "input": {
      "debug": false,
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "How do Sun and Earth sensors boost spacecraft navigation and mission success?",
      "temperature": 0.75,
      "max_new_tokens": 128,
      "min_new_tokens": -1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Sun and Earth sensors play an important role in ensuring the accuracy of navigation systems and the success of spacecraft missions. Here’s how: Accurate Navigation: Sun sensors are used to accurately determine the orientation of a spacecraft with respect to the sun. This information is critical for navigating through space, as it helps keep a spacecraft on course and avoid collisions with other objects in orbit. Sun sensors can also be used to determine the position of a spacecraft relative to its surroundings, which is essential for mission planning and execution. Asteroid Probe Mission

{
  "completed_at": "2024-07-30T20:11:56.693204Z",
  "created_at": "2024-07-30T20:09:16.331000Z",
  "data_removed": false,
  "error": null,
  "id": "d5en6kq75drgg0ch0n1a584bww",
  "input": {
    "debug": false,
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "How do Sun and Earth sensors boost spacecraft navigation and mission success?",
    "temperature": 0.75,
    "max_new_tokens": 128,
    "min_new_tokens": -1
  },
  "logs": "Your formatted prompt is:\nHow do Sun and Earth sensors boost spacecraft navigation and mission success?\nprevious weights were different, switching to https://replicate.delivery/pbxt/rSIuuP8T2eUOJarWa0ZDrY3orSuayx7xBIJjIUmqll9nJxmJA/training_output.zip\nDownloading peft weights\nusing https://replicate.delivery/pbxt/rSIuuP8T2eUOJarWa0ZDrY3orSuayx7xBIJjIUmqll9nJxmJA/training_output.zip instead of https://replicate.delivery/pbxt/rSIuuP8T2eUOJarWa0ZDrY3orSuayx7xBIJjIUmqll9nJxmJA/training_output.zip\nDownloaded training_output.zip as 10 824 kB chunks in 0.3842 with 0 retries\nDownloaded peft weights in 0.384\nUnzipped peft weights in 0.017\nInitialized peft model in 0.008\nOverall initialize_peft took 9.953\nExllama: False\nINFO 07-30 20:11:53 async_llm_engine.py:371] Received request 0: prompt: 'How do Sun and Earth sensors boost spacecraft navigation and mission success?', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=1.0, temperature=0.75, top_p=0.9, top_k=50, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['</s>'], ignore_eos=False, max_tokens=128, logprobs=None, skip_special_tokens=True), prompt token ids: None.\nINFO 07-30 20:11:53 llm_engine.py:631] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%\nINFO 07-30 20:11:56 async_llm_engine.py:111] Finished request 0.\nhostname: model-hp-73001d654114dad81ec65da3b834e2f6-888dc6d68-m2gtq",
  "metrics": {
    "predict_time": 13.046766136,
    "total_time": 160.362204
  },
  "output": [
    "\n",
    "S",
    "un",
    " and",
    " Earth",
    " sens",
    "ors",
    " play",
    " an",
    " important",
    " role",
    " in",
    " ens",
    "uring",
    " the",
    " accuracy",
    " of",
    " navigation",
    " systems",
    " and",
    " the",
    " success",
    " of",
    " space",
    "craft",
    " miss",
    "ions",
    ".",
    " Here",
    "’",
    "s",
    " how",
    ":",
    "\n",
    "Acc",
    "ur",
    "ate",
    " Navigation",
    ":",
    " Sun",
    " sens",
    "ors",
    " are",
    " used",
    " to",
    " accur",
    "ately",
    " determine",
    " the",
    " orientation",
    " of",
    " a",
    " space",
    "craft",
    " with",
    " respect",
    " to",
    " the",
    " sun",
    ".",
    " This",
    " information",
    " is",
    " critical",
    " for",
    " navig",
    "ating",
    " through",
    " space",
    ",",
    " as",
    " it",
    " helps",
    " keep",
    " a",
    " space",
    "craft",
    " on",
    " course",
    " and",
    " avoid",
    " coll",
    "isions",
    " with",
    " other",
    " objects",
    " in",
    " orbit",
    ".",
    " Sun",
    " sens",
    "ors",
    " can",
    " also",
    " be",
    " used",
    " to",
    " determine",
    " the",
    " position",
    " of",
    " a",
    " space",
    "craft",
    " relative",
    " to",
    " its",
    " surr",
    "ound",
    "ings",
    ",",
    " which",
    " is",
    " essential",
    " for",
    " mission",
    " planning",
    " and",
    " execution",
    ".",
    "\n",
    "A",
    "st",
    "ero",
    "id",
    " Pro",
    "be",
    " Mission"
  ],
  "started_at": "2024-07-30T20:11:43.646438Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/b4fko4z7r3tfa5euybmqkaav4dwjow24mjrybel6gccnujung2tq",
    "get": "https://api.replicate.com/v1/predictions/d5en6kq75drgg0ch0n1a584bww",
    "cancel": "https://api.replicate.com/v1/predictions/d5en6kq75drgg0ch0n1a584bww/cancel"
  },
  "version": "fd8ed7161c14133273cfa8fdc60a10143a0107a7d4adeb495ba98f22257d965e"
}

Generated in

13.1 seconds

Tweak it Share Report

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

CosmoSpeak

</center>

Model Summary

CosmoSpeak is a state-of-the-art chatbot that specializes in the domain of Astronautics / Space Mission Engineering. It covers topics such as

.Flight control team .Flight Dynamics .Procedure Preparation and Validation .Mission Planning .Extravehicular Activities (EVAs) .Collision Avoidance Manoeuvres .Mission Termination and De-Orbit Strategies

CosmoSpeak is a fine-tuned Llama-7B trained with Astrochat dataset (https://huggingface.co/datasets/patrickfleith/AstroChat)