lucataco / ollama-qwq

Ollama QwQ 32B (Updated 6 months ago)

Cold

Public
56 runs
L40S
GitHub
Weights
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207

Model

lucataco/ollama-qwq:4bfc56cd

1yr6zwrzwnrme0cktawa1j5yjr

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

81.9s

Created

6 months ago

Input

top_p: 0.95
prompt: How many r in strawberry
max_tokens: 512
temperature: 0.7

{
  "top_p": 0.95,
  "prompt": "How many r in strawberry",
  "max_tokens": 512,
  "temperature": 0.7
}

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 lucataco/ollama-qwq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207",
  {
    input: {
      top_p: 0.95,
      prompt: "How many r in strawberry",
      max_tokens: 512,
      temperature: 0.7
    }
  }
);

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 lucataco/ollama-qwq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207",
    input={
        "top_p": 0.95,
        "prompt": "How many r in strawberry",
        "max_tokens": 512,
        "temperature": 0.7
    }
)

# The lucataco/ollama-qwq 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/lucataco/ollama-qwq/api#output-schema
    print(item, end="")

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

Run lucataco/ollama-qwq 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": "lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207",
    "input": {
      "top_p": 0.95,
      "prompt": "How many r in strawberry",
      "max_tokens": 512,
      "temperature": 0.7
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Let's see... the word is "strawberry." I need to find out how many 'r's are in it. Okay, let's spell it out slowly: S-T-R-A-W-B-E-R-R-Y. I can see that there are 'r's in there. Let me count them one by one. First, I look at each letter: S is not r, T is not r, R is an r—so that's one, A is not r, W is not r, B is not r, E is not r, R is another r—so now that's two, R is another r—so that makes three, And Y is not r. So, total 'r's in "strawberry" are three. But wait, let me double-check. Sometimes I might miss one if I'm not careful. Spell it again: S-T-R-A-W-B-E-R-R-Y. Start counting again: The first R is the third letter, The second R is the ninth letter, The third R is the tenth letter. Yes, three 'r's in "strawberry." I think that's correct. **Final Answer** \[ \boxed{3} \]

{
  "completed_at": "2024-12-17T03:46:24.358594Z",
  "created_at": "2024-12-17T03:45:02.437000Z",
  "data_removed": false,
  "error": null,
  "id": "1yr6zwrzwnrme0cktawa1j5yjr",
  "input": {
    "top_p": 0.95,
    "prompt": "How many r in strawberry",
    "max_tokens": 512,
    "temperature": 0.7
  },
  "logs": null,
  "metrics": {
    "predict_time": 8.788645682,
    "total_time": 81.921594
  },
  "output": [
    "Let",
    "'s",
    " see",
    "...",
    " the",
    " word",
    " is",
    " \"",
    "str",
    "aw",
    "berry",
    ".\"",
    " I",
    " need",
    " to",
    " find",
    " out",
    " how",
    " many",
    " '",
    "r",
    "'s",
    " are",
    " in",
    " it",
    ".",
    " Okay",
    ",",
    " let",
    "'s",
    " spell",
    " it",
    " out",
    " slowly",
    ":",
    " S",
    "-T",
    "-R",
    "-A",
    "-W",
    "-B",
    "-E",
    "-R",
    "-R",
    "-Y",
    ".",
    " I",
    " can",
    " see",
    " that",
    " there",
    " are",
    " '",
    "r",
    "'s",
    " in",
    " there",
    ".",
    " Let",
    " me",
    " count",
    " them",
    " one",
    " by",
    " one",
    ".\n\n",
    "First",
    ",",
    " I",
    " look",
    " at",
    " each",
    " letter",
    ":\n\n",
    "S",
    " is",
    " not",
    " r",
    ",\n\n",
    "T",
    " is",
    " not",
    " r",
    ",\n\n",
    "R",
    " is",
    " an",
    " r",
    "—",
    "so",
    " that",
    "'s",
    " one",
    ",\n\n",
    "A",
    " is",
    " not",
    " r",
    ",\n\n",
    "W",
    " is",
    " not",
    " r",
    ",\n\n",
    "B",
    " is",
    " not",
    " r",
    ",\n\n",
    "E",
    " is",
    " not",
    " r",
    ",\n\n",
    "R",
    " is",
    " another",
    " r",
    "—",
    "so",
    " now",
    " that",
    "'s",
    " two",
    ",\n\n",
    "R",
    " is",
    " another",
    " r",
    "—",
    "so",
    " that",
    " makes",
    " three",
    ",\n\n",
    "And",
    " Y",
    " is",
    " not",
    " r",
    ".\n\n",
    "So",
    ",",
    " total",
    " '",
    "r",
    "'s",
    " in",
    " \"",
    "str",
    "aw",
    "berry",
    "\"",
    " are",
    " three",
    ".\n\n",
    "But",
    " wait",
    ",",
    " let",
    " me",
    " double",
    "-check",
    ".",
    " Sometimes",
    " I",
    " might",
    " miss",
    " one",
    " if",
    " I",
    "'m",
    " not",
    " careful",
    ".\n\n",
    "Spell",
    " it",
    " again",
    ":",
    " S",
    "-T",
    "-R",
    "-A",
    "-W",
    "-B",
    "-E",
    "-R",
    "-R",
    "-Y",
    ".\n\n",
    "Start",
    " counting",
    " again",
    ":\n\n",
    "The",
    " first",
    " R",
    " is",
    " the",
    " third",
    " letter",
    ",\n\n",
    "The",
    " second",
    " R",
    " is",
    " the",
    " ninth",
    " letter",
    ",\n\n",
    "The",
    " third",
    " R",
    " is",
    " the",
    " tenth",
    " letter",
    ".\n\n",
    "Yes",
    ",",
    " three",
    " '",
    "r",
    "'s",
    " in",
    " \"",
    "str",
    "aw",
    "berry",
    ".\"\n\n",
    "I",
    " think",
    " that",
    "'s",
    " correct",
    ".\n\n",
    "**",
    "Final",
    " Answer",
    "**\n\n",
    "\\[",
    " \\",
    "boxed",
    "{",
    "3",
    "}",
    " \\",
    "]",
    ""
  ],
  "started_at": "2024-12-17T03:46:15.569948Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/brlesucuu34twpbr4b64bj4de4sjlv7p4ajs5lv6wlusc2adibiq",
    "get": "https://api.replicate.com/v1/predictions/1yr6zwrzwnrme0cktawa1j5yjr",
    "cancel": "https://api.replicate.com/v1/predictions/1yr6zwrzwnrme0cktawa1j5yjr/cancel"
  },
  "version": "4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207"
}

Generated in

8.8 seconds

Tweak it Share Report View full prediction

Prediction

lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207

Model

lucataco/ollama-qwq:4bfc56cd

z1v04rr8jhrm80cktb0bhdg9zg

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

11.5s

Created

6 months ago

Input

top_p: 0.95
prompt: How many r in strawberry
max_tokens: 512
temperature: 0.7

{
  "top_p": 0.95,
  "prompt": "How many r in strawberry",
  "max_tokens": 512,
  "temperature": 0.7
}

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 lucataco/ollama-qwq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207",
  {
    input: {
      top_p: 0.95,
      prompt: "How many r in strawberry",
      max_tokens: 512,
      temperature: 0.7
    }
  }
);

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 lucataco/ollama-qwq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207",
    input={
        "top_p": 0.95,
        "prompt": "How many r in strawberry",
        "max_tokens": 512,
        "temperature": 0.7
    }
)

# The lucataco/ollama-qwq 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/lucataco/ollama-qwq/api#output-schema
    print(item, end="")

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

Run lucataco/ollama-qwq 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": "lucataco/ollama-qwq:4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207",
    "input": {
      "top_p": 0.95,
      "prompt": "How many r in strawberry",
      "max_tokens": 512,
      "temperature": 0.7
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Let's see... the word is "strawberry." I need to find out how many 'r's are in it. Okay, let's spell it out slowly: S-T-R-A-W-B-E-R-R-Y. I can see that there are two 'r's in the word. Wait, let me check again because sometimes letters can be tricky. S-T-R-A-W-B-E-R-R-Y. Yes, there's an 'r' after the s, then another one between e and y at the end. So that's two 'r's. I think that's correct. But just to be sure, maybe I should look it up or have someone else check it. But I'm pretty confident that there are two 'r's in "strawberry." Maybe I can count the letters one by one: S is 1, T is 2, R is 3, A is 4, W is 5, B is 6, E is 7, R is 8, R is 9, Y is 10. Wait, that says there are three 'r's. But earlier I thought there were only two. Hmm, maybe I miscounted. Let me do it again: S-T-R-A-W-B-E-R-R-Y. Okay, first 'r' is the third letter, then another one before the last letter, and another one before that. So yes, there are three 'r's. I don't know why I thought there were only two earlier. Maybe I skipped one. So, the correct answer is three 'r's in "strawberry." I should remember that for future reference.

{
  "completed_at": "2024-12-17T03:53:52.231685Z",
  "created_at": "2024-12-17T03:53:40.756000Z",
  "data_removed": false,
  "error": null,
  "id": "z1v04rr8jhrm80cktb0bhdg9zg",
  "input": {
    "top_p": 0.95,
    "prompt": "How many r in strawberry",
    "max_tokens": 512,
    "temperature": 0.7
  },
  "logs": null,
  "metrics": {
    "predict_time": 11.467124757,
    "total_time": 11.475685
  },
  "output": [
    "Let",
    "'s",
    " see",
    "...",
    " the",
    " word",
    " is",
    " \"",
    "str",
    "aw",
    "berry",
    ".\"",
    " I",
    " need",
    " to",
    " find",
    " out",
    " how",
    " many",
    " '",
    "r",
    "'s",
    " are",
    " in",
    " it",
    ".",
    " Okay",
    ",",
    " let",
    "'s",
    " spell",
    " it",
    " out",
    " slowly",
    ":",
    " S",
    "-T",
    "-R",
    "-A",
    "-W",
    "-B",
    "-E",
    "-R",
    "-R",
    "-Y",
    ".",
    " I",
    " can",
    " see",
    " that",
    " there",
    " are",
    " two",
    " '",
    "r",
    "'s",
    " in",
    " the",
    " word",
    ".",
    " Wait",
    ",",
    " let",
    " me",
    " check",
    " again",
    " because",
    " sometimes",
    " letters",
    " can",
    " be",
    " tricky",
    ".",
    " S",
    "-T",
    "-R",
    "-A",
    "-W",
    "-B",
    "-E",
    "-R",
    "-R",
    "-Y",
    ".",
    " Yes",
    ",",
    " there",
    "'s",
    " an",
    " '",
    "r",
    "'",
    " after",
    " the",
    " s",
    ",",
    " then",
    " another",
    " one",
    " between",
    " e",
    " and",
    " y",
    " at",
    " the",
    " end",
    ".",
    " So",
    " that",
    "'s",
    " two",
    " '",
    "r",
    "'s",
    ".",
    " I",
    " think",
    " that",
    "'s",
    " correct",
    ".",
    " But",
    " just",
    " to",
    " be",
    " sure",
    ",",
    " maybe",
    " I",
    " should",
    " look",
    " it",
    " up",
    " or",
    " have",
    " someone",
    " else",
    " check",
    " it",
    ".",
    " But",
    " I",
    "'m",
    " pretty",
    " confident",
    " that",
    " there",
    " are",
    " two",
    " '",
    "r",
    "'s",
    " in",
    " \"",
    "str",
    "aw",
    "berry",
    ".\"",
    " Maybe",
    " I",
    " can",
    " count",
    " the",
    " letters",
    " one",
    " by",
    " one",
    ":",
    " S",
    " is",
    " ",
    "1",
    ",",
    " T",
    " is",
    " ",
    "2",
    ",",
    " R",
    " is",
    " ",
    "3",
    ",",
    " A",
    " is",
    " ",
    "4",
    ",",
    " W",
    " is",
    " ",
    "5",
    ",",
    " B",
    " is",
    " ",
    "6",
    ",",
    " E",
    " is",
    " ",
    "7",
    ",",
    " R",
    " is",
    " ",
    "8",
    ",",
    " R",
    " is",
    " ",
    "9",
    ",",
    " Y",
    " is",
    " ",
    "1",
    "0",
    ".",
    " Wait",
    ",",
    " that",
    " says",
    " there",
    " are",
    " three",
    " '",
    "r",
    "'s",
    ".",
    " But",
    " earlier",
    " I",
    " thought",
    " there",
    " were",
    " only",
    " two",
    ".",
    " Hmm",
    ",",
    " maybe",
    " I",
    " mis",
    "count",
    "ed",
    ".",
    " Let",
    " me",
    " do",
    " it",
    " again",
    ":",
    " S",
    "-T",
    "-R",
    "-A",
    "-W",
    "-B",
    "-E",
    "-R",
    "-R",
    "-Y",
    ".",
    " Okay",
    ",",
    " first",
    " '",
    "r",
    "'",
    " is",
    " the",
    " third",
    " letter",
    ",",
    " then",
    " another",
    " one",
    " before",
    " the",
    " last",
    " letter",
    ",",
    " and",
    " another",
    " one",
    " before",
    " that",
    ".",
    " So",
    " yes",
    ",",
    " there",
    " are",
    " three",
    " '",
    "r",
    "'s",
    ".",
    " I",
    " don",
    "'t",
    " know",
    " why",
    " I",
    " thought",
    " there",
    " were",
    " only",
    " two",
    " earlier",
    ".",
    " Maybe",
    " I",
    " skipped",
    " one",
    ".",
    " So",
    ",",
    " the",
    " correct",
    " answer",
    " is",
    " three",
    " '",
    "r",
    "'s",
    " in",
    " \"",
    "str",
    "aw",
    "berry",
    ".\"",
    " I",
    " should",
    " remember",
    " that",
    " for",
    " future",
    " reference",
    ".",
    ""
  ],
  "started_at": "2024-12-17T03:53:40.764560Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/ag3tnhnx7c2uh2cstb2ancc3xw4gg7tljlapydheo73q6ql3cgnq",
    "get": "https://api.replicate.com/v1/predictions/z1v04rr8jhrm80cktb0bhdg9zg",
    "cancel": "https://api.replicate.com/v1/predictions/z1v04rr8jhrm80cktb0bhdg9zg/cancel"
  },
  "version": "4bfc56cd5731ba68a0cbc95e40fe670b7780dd61f2c53e09411e4154f7a70207"
}

Generated in

11.5 seconds

Tweak it Share Report View full prediction