Prediction

nateraw/samsum-llama-7b:16665c1f

Model

nateraw/samsum-llama-7b:16665c1f

ID

o2ispslbunyagtkbnjeorljenq

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

42.2s

Created

over 1 year ago

Input

debug
top_k: 50
top_p: 0.95
prompt: [INST] <<SYS>> Use the Input to provide a summary of a conversation. <</SYS>> Input: LUKE: (Struggling to maintain his balance on the platform, his hand severed) You killed my father! VADER: No, Luke. I am your father. LUKE: (Horrified) No. No! That's not true! That's impossible! VADER: Search your feelings; you know it to be true. LUKE: NOOOOOOO! NOOOOOO! Summary:
temperature: 0.4
max_new_tokens: 181
min_new_tokens: 8
stop_sequences: </s>

{
  "debug": false,
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLUKE: (Struggling to maintain his balance on the platform, his hand severed) You killed my father!\nVADER: No, Luke. I am your father.\nLUKE: (Horrified) No. No! That's not true! That's impossible!\nVADER: Search your feelings; you know it to be true.\nLUKE: NOOOOOOO! NOOOOOO!\n\nSummary: ",
  "temperature": 0.4,
  "max_new_tokens": 181,
  "min_new_tokens": 8,
  "stop_sequences": "</s>"
}

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 nateraw/samsum-llama-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nateraw/samsum-llama-7b:16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
  {
    input: {
      debug: false,
      top_k: 50,
      top_p: 0.95,
      prompt: "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLUKE: (Struggling to maintain his balance on the platform, his hand severed) You killed my father!\nVADER: No, Luke. I am your father.\nLUKE: (Horrified) No. No! That's not true! That's impossible!\nVADER: Search your feelings; you know it to be true.\nLUKE: NOOOOOOO! NOOOOOO!\n\nSummary: ",
      temperature: 0.4,
      max_new_tokens: 181,
      min_new_tokens: 8,
      stop_sequences: "</s>"
    }
  }
);
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 nateraw/samsum-llama-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/samsum-llama-7b:16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
    input={
        "debug": False,
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLUKE: (Struggling to maintain his balance on the platform, his hand severed) You killed my father!\nVADER: No, Luke. I am your father.\nLUKE: (Horrified) No. No! That's not true! That's impossible!\nVADER: Search your feelings; you know it to be true.\nLUKE: NOOOOOOO! NOOOOOO!\n\nSummary: ",
        "temperature": 0.4,
        "max_new_tokens": 181,
        "min_new_tokens": 8,
        "stop_sequences": "</s>"
    }
)

# The nateraw/samsum-llama-7b 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/nateraw/samsum-llama-7b/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 nateraw/samsum-llama-7b 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": "16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
    "input": {
      "debug": false,
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "[INST] <<SYS>>\\nUse the Input to provide a summary of a conversation.\\n<</SYS>>\\n\\nInput:\\nLUKE: (Struggling to maintain his balance on the platform, his hand severed) You killed my father!\\nVADER: No, Luke. I am your father.\\nLUKE: (Horrified) No. No! That\'s not true! That\'s impossible!\\nVADER: Search your feelings; you know it to be true.\\nLUKE: NOOOOOOO! NOOOOOO!\\n\\nSummary: ",
      "temperature": 0.4,
      "max_new_tokens": 181,
      "min_new_tokens": 8,
      "stop_sequences": "</s>"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Luke is horrified to learn that Vader is his father.

Generated in

0.7 seconds

Tweak it Share Report

Prediction

nateraw/samsum-llama-7b:16665c1f

Model

nateraw/samsum-llama-7b:16665c1f

ID

zyfehl3b744jakuvghnulajhya

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

0.7s

Created

over 1 year ago by @nateraw

Input

debug
top_k: 50
top_p: 0.95
prompt: [INST] <<SYS>> Use the Input to provide a summary of a conversation. <</SYS>> Input: Harry: Who are you? Hagrid: Rubeus Hagrid, Keeper of Keys and Grounds at Hogwarts. Of course, you know all about Hogwarts. Harry: Sorry, no. Hagrid: No? Blimey, Harry, did you never wonder where yer parents learned it all? Harry: All what? Hagrid: Yer a wizard, Harry. Harry: I-- I'm a what? Hagrid: A wizard! And a thumpin' good 'un, I'll wager, once you've been trained up a bit. [/INST] Summary:
temperature: 0.4
max_new_tokens: 256
min_new_tokens: -1
stop_sequences: </s>

{
  "debug": false,
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nHarry: Who are you?\nHagrid: Rubeus Hagrid, Keeper of Keys and Grounds at Hogwarts. Of course, you know all about Hogwarts.\nHarry: Sorry, no.\nHagrid: No? Blimey, Harry, did you never wonder where yer parents learned it all?\nHarry: All what?\nHagrid: Yer a wizard, Harry.\nHarry: I-- I'm a what?\nHagrid: A wizard! And a thumpin' good 'un, I'll wager, once you've been trained up a bit. [/INST]\n\nSummary: ",
  "temperature": 0.4,
  "max_new_tokens": 256,
  "min_new_tokens": -1,
  "stop_sequences": "</s>"
}

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 nateraw/samsum-llama-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nateraw/samsum-llama-7b:16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
  {
    input: {
      debug: false,
      top_k: 50,
      top_p: 0.95,
      prompt: "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nHarry: Who are you?\nHagrid: Rubeus Hagrid, Keeper of Keys and Grounds at Hogwarts. Of course, you know all about Hogwarts.\nHarry: Sorry, no.\nHagrid: No? Blimey, Harry, did you never wonder where yer parents learned it all?\nHarry: All what?\nHagrid: Yer a wizard, Harry.\nHarry: I-- I'm a what?\nHagrid: A wizard! And a thumpin' good 'un, I'll wager, once you've been trained up a bit. [/INST]\n\nSummary: ",
      temperature: 0.4,
      max_new_tokens: 256,
      min_new_tokens: -1,
      stop_sequences: "</s>"
    }
  }
);
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 nateraw/samsum-llama-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/samsum-llama-7b:16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
    input={
        "debug": False,
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nHarry: Who are you?\nHagrid: Rubeus Hagrid, Keeper of Keys and Grounds at Hogwarts. Of course, you know all about Hogwarts.\nHarry: Sorry, no.\nHagrid: No? Blimey, Harry, did you never wonder where yer parents learned it all?\nHarry: All what?\nHagrid: Yer a wizard, Harry.\nHarry: I-- I'm a what?\nHagrid: A wizard! And a thumpin' good 'un, I'll wager, once you've been trained up a bit. [/INST]\n\nSummary: ",
        "temperature": 0.4,
        "max_new_tokens": 256,
        "min_new_tokens": -1,
        "stop_sequences": "</s>"
    }
)

# The nateraw/samsum-llama-7b 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/nateraw/samsum-llama-7b/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 nateraw/samsum-llama-7b 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": "16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
    "input": {
      "debug": false,
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "[INST] <<SYS>>\\nUse the Input to provide a summary of a conversation.\\n<</SYS>>\\n\\nInput:\\nHarry: Who are you?\\nHagrid: Rubeus Hagrid, Keeper of Keys and Grounds at Hogwarts. Of course, you know all about Hogwarts.\\nHarry: Sorry, no.\\nHagrid: No? Blimey, Harry, did you never wonder where yer parents learned it all?\\nHarry: All what?\\nHagrid: Yer a wizard, Harry.\\nHarry: I-- I\'m a what?\\nHagrid: A wizard! And a thumpin\' good \'un, I\'ll wager, once you\'ve been trained up a bit. [/INST]\\n\\nSummary: ",
      "temperature": 0.4,
      "max_new_tokens": 256,
      "min_new_tokens": -1,
      "stop_sequences": "</s>"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Harry is a wizard.

Generated in

0.7 seconds

Tweak it Share Report

Prediction

nateraw/samsum-llama-7b:16665c1f

Model

nateraw/samsum-llama-7b:16665c1f

ID

qtq6colbqyj6rxq6zmuwax3wia

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

1.4s

Created

over 1 year ago

Input

debug
top_k: 50
top_p: 0.95
prompt: [INST] <<SYS>> Use the Input to provide a summary of a conversation. <</SYS>> Input: Liam: did you see that new movie that just came out? Liam: "Starry Skies" I think it's called Ava: oh yeah, I heard about it Liam: it's about this astronaut who gets lost in space Liam: and he has to find his way back to earth Ava: sounds intense Liam: it was! there were so many moments where I thought he wouldn't make it Ava: i need to watch it then, been looking for a good movie Liam: highly recommend it! Ava: thanks for the suggestion Liam! Liam: anytime, always happy to share good movies Ava: let's plan to watch it together sometime Liam: sounds like a plan! Summary:
temperature: 0.4
max_new_tokens: 181
min_new_tokens: -1
stop_sequences: </s>

{
  "debug": false,
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLiam: did you see that new movie that just came out?\nLiam: \"Starry Skies\" I think it's called \nAva: oh yeah, I heard about it \nLiam: it's about this astronaut who gets lost in space \nLiam: and he has to find his way back to earth \nAva: sounds intense \nLiam: it was! there were so many moments where I thought he wouldn't make it \nAva: i need to watch it then, been looking for a good movie \nLiam: highly recommend it! \nAva: thanks for the suggestion Liam! \nLiam: anytime, always happy to share good movies \nAva: let's plan to watch it together sometime \nLiam: sounds like a plan! \n\nSummary: ",
  "temperature": 0.4,
  "max_new_tokens": 181,
  "min_new_tokens": -1,
  "stop_sequences": "</s>"
}

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 nateraw/samsum-llama-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nateraw/samsum-llama-7b:16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
  {
    input: {
      debug: false,
      top_k: 50,
      top_p: 0.95,
      prompt: "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLiam: did you see that new movie that just came out?\nLiam: \"Starry Skies\" I think it's called \nAva: oh yeah, I heard about it \nLiam: it's about this astronaut who gets lost in space \nLiam: and he has to find his way back to earth \nAva: sounds intense \nLiam: it was! there were so many moments where I thought he wouldn't make it \nAva: i need to watch it then, been looking for a good movie \nLiam: highly recommend it! \nAva: thanks for the suggestion Liam! \nLiam: anytime, always happy to share good movies \nAva: let's plan to watch it together sometime \nLiam: sounds like a plan! \n\nSummary: ",
      temperature: 0.4,
      max_new_tokens: 181,
      min_new_tokens: -1,
      stop_sequences: "</s>"
    }
  }
);
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 nateraw/samsum-llama-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/samsum-llama-7b:16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
    input={
        "debug": False,
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLiam: did you see that new movie that just came out?\nLiam: \"Starry Skies\" I think it's called \nAva: oh yeah, I heard about it \nLiam: it's about this astronaut who gets lost in space \nLiam: and he has to find his way back to earth \nAva: sounds intense \nLiam: it was! there were so many moments where I thought he wouldn't make it \nAva: i need to watch it then, been looking for a good movie \nLiam: highly recommend it! \nAva: thanks for the suggestion Liam! \nLiam: anytime, always happy to share good movies \nAva: let's plan to watch it together sometime \nLiam: sounds like a plan! \n\nSummary: ",
        "temperature": 0.4,
        "max_new_tokens": 181,
        "min_new_tokens": -1,
        "stop_sequences": "</s>"
    }
)

# The nateraw/samsum-llama-7b 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/nateraw/samsum-llama-7b/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 nateraw/samsum-llama-7b 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": "16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9",
    "input": {
      "debug": false,
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "[INST] <<SYS>>\\nUse the Input to provide a summary of a conversation.\\n<</SYS>>\\n\\nInput:\\nLiam: did you see that new movie that just came out?\\nLiam: \\"Starry Skies\\" I think it\'s called \\nAva: oh yeah, I heard about it \\nLiam: it\'s about this astronaut who gets lost in space \\nLiam: and he has to find his way back to earth \\nAva: sounds intense \\nLiam: it was! there were so many moments where I thought he wouldn\'t make it \\nAva: i need to watch it then, been looking for a good movie \\nLiam: highly recommend it! \\nAva: thanks for the suggestion Liam! \\nLiam: anytime, always happy to share good movies \\nAva: let\'s plan to watch it together sometime \\nLiam: sounds like a plan! \\n\\nSummary: ",
      "temperature": 0.4,
      "max_new_tokens": 181,
      "min_new_tokens": -1,
      "stop_sequences": "</s>"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Ava and Liam are going to watch the movie "Starry Skies".

{
  "completed_at": "2023-09-06T00:06:29.446296Z",
  "created_at": "2023-09-06T00:06:28.105118Z",
  "data_removed": false,
  "error": null,
  "id": "qtq6colbqyj6rxq6zmuwax3wia",
  "input": {
    "debug": false,
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nLiam: did you see that new movie that just came out?\nLiam: \"Starry Skies\" I think it's called \nAva: oh yeah, I heard about it \nLiam: it's about this astronaut who gets lost in space \nLiam: and he has to find his way back to earth \nAva: sounds intense \nLiam: it was! there were so many moments where I thought he wouldn't make it \nAva: i need to watch it then, been looking for a good movie \nLiam: highly recommend it! \nAva: thanks for the suggestion Liam! \nLiam: anytime, always happy to share good movies \nAva: let's plan to watch it together sometime \nLiam: sounds like a plan! \n\nSummary: ",
    "temperature": 0.4,
    "max_new_tokens": 181,
    "min_new_tokens": -1,
    "stop_sequences": "</s>"
  },
  "logs": "Your formatted prompt is:\n[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\nInput:\nLiam: did you see that new movie that just came out?\nLiam: \"Starry Skies\" I think it's called\nAva: oh yeah, I heard about it\nLiam: it's about this astronaut who gets lost in space\nLiam: and he has to find his way back to earth\nAva: sounds intense\nLiam: it was! there were so many moments where I thought he wouldn't make it\nAva: i need to watch it then, been looking for a good movie\nLiam: highly recommend it!\nAva: thanks for the suggestion Liam!\nLiam: anytime, always happy to share good movies\nAva: let's plan to watch it together sometime\nLiam: sounds like a plan!\nSummary:",
  "metrics": {
    "predict_time": 1.35948,
    "total_time": 1.341178
  },
  "output": [
    " A",
    "va",
    " and",
    " Li",
    "am",
    " are",
    " going",
    " to",
    " watch",
    " the",
    " movie",
    " \"",
    "Star",
    "ry",
    " Sk",
    "ies",
    "\"."
  ],
  "started_at": "2023-09-06T00:06:28.086816Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/qtq6colbqyj6rxq6zmuwax3wia",
    "cancel": "https://api.replicate.com/v1/predictions/qtq6colbqyj6rxq6zmuwax3wia/cancel"
  },
  "version": "16665c1f00ad4d5d6c88393aa05390cf4d9f4e49c8abde4c58f2e1e71fd806f9"
}

Generated in

1.4 seconds

Tweak it Share Report

nateraw / samsum-llama-7b

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (o2ispslbunyagtkbnjeorljenq)

Logs (zyfehl3b744jakuvghnulajhya)

Logs (qtq6colbqyj6rxq6zmuwax3wia)