Readme
Output is a dictionary with key ‘mostLikelyClass’ giving the most likely class and key ‘allClasses’ giving a dictionary of all class likelihoods.
georgedavila
/
bart-large-mnli-classifier
Zero-shot classifier which classifies text into categories of your choosing. Returns a dictionary of the most likely class and all class likelihoods.
- Public
- 3.6K runs
-
T4
- GitHub
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=georgedavila/bart-large-mnli-classifier
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet 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 georgedavila/bart-large-mnli-classifier using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"georgedavila/bart-large-mnli-classifier:d929487cf059f96a17752ebe55ae5a85b2e8be6cd627078e49c6caa2fd4213db",
{
input: {
labels: "Cooking Instructions, Question about Astronomy",
text2classify: "Add salt to boiling water to prevent pasta from sticking together"
}
}
);
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 replicateSet 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 replicateRun georgedavila/bart-large-mnli-classifier using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"georgedavila/bart-large-mnli-classifier:d929487cf059f96a17752ebe55ae5a85b2e8be6cd627078e49c6caa2fd4213db",
input={
"labels": "Cooking Instructions, Question about Astronomy",
"text2classify": "Add salt to boiling water to prevent pasta from sticking together"
}
)
print(output)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 georgedavila/bart-large-mnli-classifier 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": "d929487cf059f96a17752ebe55ae5a85b2e8be6cd627078e49c6caa2fd4213db",
"input": {
"labels": "Cooking Instructions, Question about Astronomy",
"text2classify": "Add salt to boiling water to prevent pasta from sticking together"
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"allClasses": {
"Cooking Instructions": 0.9597448110580444,
"Question about Astronomy": 0.04025513678789139
},
"mostLikelyClass": "Cooking Instructions"
}
{
"completed_at": "2024-01-03T01:30:08.099531Z",
"created_at": "2024-01-03T01:28:02.416962Z",
"data_removed": false,
"error": null,
"id": "wwjcl6rbtjkwtyy43knkb462fm",
"input": {
"labels": "Cooking Instructions, Question about Astronomy",
"text2classify": "Add salt to boiling water to prevent pasta from sticking together"
},
"logs": "config.json: 0%| | 0.00/1.15k [00:00<?, ?B/s]\nconfig.json: 100%|██████████| 1.15k/1.15k [00:00<00:00, 5.85MB/s]\nmodel.safetensors: 0%| | 0.00/1.63G [00:00<?, ?B/s]\nmodel.safetensors: 1%| | 10.5M/1.63G [00:00<00:39, 41.3MB/s]\nmodel.safetensors: 2%|▏ | 31.5M/1.63G [00:00<00:15, 100MB/s] \nmodel.safetensors: 3%|▎ | 52.4M/1.63G [00:00<00:12, 129MB/s]\nmodel.safetensors: 5%|▍ | 73.4M/1.63G [00:00<00:11, 131MB/s]\nmodel.safetensors: 6%|▌ | 94.4M/1.63G [00:00<00:10, 140MB/s]\nmodel.safetensors: 7%|▋ | 115M/1.63G [00:00<00:09, 158MB/s] \nmodel.safetensors: 8%|▊ | 136M/1.63G [00:00<00:08, 169MB/s]\nmodel.safetensors: 10%|▉ | 157M/1.63G [00:01<00:08, 167MB/s]\nmodel.safetensors: 11%|█ | 178M/1.63G [00:01<00:08, 178MB/s]\nmodel.safetensors: 12%|█▏ | 199M/1.63G [00:01<00:08, 177MB/s]\nmodel.safetensors: 14%|█▎ | 220M/1.63G [00:01<00:07, 183MB/s]\nmodel.safetensors: 15%|█▍ | 241M/1.63G [00:01<00:07, 186MB/s]\nmodel.safetensors: 16%|█▌ | 262M/1.63G [00:01<00:07, 189MB/s]\nmodel.safetensors: 17%|█▋ | 283M/1.63G [00:01<00:06, 193MB/s]\nmodel.safetensors: 19%|█▉ | 315M/1.63G [00:01<00:06, 199MB/s]\nmodel.safetensors: 21%|██ | 336M/1.63G [00:02<00:06, 198MB/s]\nmodel.safetensors: 22%|██▏ | 357M/1.63G [00:02<00:06, 200MB/s]\nmodel.safetensors: 23%|██▎ | 377M/1.63G [00:02<00:06, 197MB/s]\nmodel.safetensors: 24%|██▍ | 398M/1.63G [00:02<00:06, 197MB/s]\nmodel.safetensors: 26%|██▋ | 430M/1.63G [00:02<00:05, 202MB/s]\nmodel.safetensors: 28%|██▊ | 461M/1.63G [00:02<00:05, 206MB/s]\nmodel.safetensors: 30%|███ | 493M/1.63G [00:02<00:05, 209MB/s]\nmodel.safetensors: 32%|███▏ | 524M/1.63G [00:02<00:05, 208MB/s]\nmodel.safetensors: 33%|███▎ | 545M/1.63G [00:03<00:05, 206MB/s]\nmodel.safetensors: 35%|███▍ | 566M/1.63G [00:03<00:05, 203MB/s]\nmodel.safetensors: 36%|███▌ | 587M/1.63G [00:03<00:05, 202MB/s]\nmodel.safetensors: 37%|███▋ | 608M/1.63G [00:03<00:05, 202MB/s]\nmodel.safetensors: 39%|███▊ | 629M/1.63G [00:03<00:04, 203MB/s]\nmodel.safetensors: 41%|████ | 661M/1.63G [00:03<00:04, 206MB/s]\nmodel.safetensors: 42%|████▏ | 682M/1.63G [00:03<00:04, 205MB/s]\nmodel.safetensors: 43%|████▎ | 703M/1.63G [00:03<00:04, 203MB/s]\nmodel.safetensors: 44%|████▍ | 724M/1.63G [00:03<00:05, 178MB/s]\nmodel.safetensors: 46%|████▌ | 744M/1.63G [00:04<00:04, 186MB/s]\nmodel.safetensors: 48%|████▊ | 776M/1.63G [00:04<00:04, 193MB/s]\nmodel.safetensors: 49%|████▉ | 797M/1.63G [00:04<00:04, 195MB/s]\nmodel.safetensors: 50%|█████ | 818M/1.63G [00:04<00:04, 198MB/s]\nmodel.safetensors: 52%|█████▏ | 849M/1.63G [00:04<00:03, 203MB/s]\nmodel.safetensors: 54%|█████▍ | 881M/1.63G [00:04<00:03, 201MB/s]\nmodel.safetensors: 55%|█████▌ | 902M/1.63G [00:04<00:03, 200MB/s]\nmodel.safetensors: 57%|█████▋ | 923M/1.63G [00:04<00:03, 199MB/s]\nmodel.safetensors: 58%|█████▊ | 944M/1.63G [00:05<00:03, 202MB/s]\nmodel.safetensors: 60%|█████▉ | 975M/1.63G [00:05<00:03, 204MB/s]\nmodel.safetensors: 61%|██████ | 996M/1.63G [00:05<00:03, 204MB/s]\nmodel.safetensors: 62%|██████▏ | 1.02G/1.63G [00:05<00:03, 200MB/s]\nmodel.safetensors: 64%|██████▎ | 1.04G/1.63G [00:05<00:02, 200MB/s]\nmodel.safetensors: 66%|██████▌ | 1.07G/1.63G [00:05<00:02, 205MB/s]\nmodel.safetensors: 67%|██████▋ | 1.09G/1.63G [00:05<00:02, 191MB/s]\nmodel.safetensors: 69%|██████▉ | 1.12G/1.63G [00:05<00:02, 199MB/s]\nmodel.safetensors: 70%|███████ | 1.14G/1.63G [00:06<00:02, 200MB/s]\nmodel.safetensors: 71%|███████▏ | 1.16G/1.63G [00:06<00:02, 201MB/s]\nmodel.safetensors: 73%|███████▎ | 1.18G/1.63G [00:06<00:02, 204MB/s]\nmodel.safetensors: 75%|███████▍ | 1.22G/1.63G [00:06<00:01, 207MB/s]\nmodel.safetensors: 77%|███████▋ | 1.25G/1.63G [00:06<00:01, 209MB/s]\nmodel.safetensors: 78%|███████▊ | 1.27G/1.63G [00:06<00:01, 182MB/s]\nmodel.safetensors: 79%|███████▉ | 1.29G/1.63G [00:06<00:01, 185MB/s]\nmodel.safetensors: 80%|████████ | 1.31G/1.63G [00:06<00:01, 172MB/s]\nmodel.safetensors: 82%|████████▏ | 1.33G/1.63G [00:07<00:01, 176MB/s]\nmodel.safetensors: 83%|████████▎ | 1.35G/1.63G [00:07<00:01, 183MB/s]\nmodel.safetensors: 84%|████████▍ | 1.37G/1.63G [00:07<00:01, 189MB/s]\nmodel.safetensors: 86%|████████▌ | 1.41G/1.63G [00:07<00:01, 198MB/s]\nmodel.safetensors: 88%|████████▊ | 1.44G/1.63G [00:07<00:01, 192MB/s]\nmodel.safetensors: 90%|█████████ | 1.47G/1.63G [00:07<00:00, 197MB/s]\nmodel.safetensors: 91%|█████████▏| 1.49G/1.63G [00:07<00:00, 199MB/s]\nmodel.safetensors: 93%|█████████▎| 1.51G/1.63G [00:07<00:00, 189MB/s]\nmodel.safetensors: 94%|█████████▍| 1.53G/1.63G [00:08<00:00, 189MB/s]\nmodel.safetensors: 95%|█████████▌| 1.55G/1.63G [00:08<00:00, 193MB/s]\nmodel.safetensors: 97%|█████████▋| 1.57G/1.63G [00:08<00:00, 178MB/s]\nmodel.safetensors: 98%|█████████▊| 1.59G/1.63G [00:08<00:00, 185MB/s]\nmodel.safetensors: 99%|█████████▉| 1.61G/1.63G [00:08<00:00, 170MB/s]\nmodel.safetensors: 100%|██████████| 1.63G/1.63G [00:08<00:00, 186MB/s]\ntokenizer_config.json: 0%| | 0.00/26.0 [00:00<?, ?B/s]\ntokenizer_config.json: 100%|██████████| 26.0/26.0 [00:00<00:00, 78.8kB/s]\nvocab.json: 0%| | 0.00/899k [00:00<?, ?B/s]\nvocab.json: 100%|██████████| 899k/899k [00:00<00:00, 9.29MB/s]\nmerges.txt: 0%| | 0.00/456k [00:00<?, ?B/s]\nmerges.txt: 100%|██████████| 456k/456k [00:00<00:00, 61.4MB/s]\ntokenizer.json: 0%| | 0.00/1.36M [00:00<?, ?B/s]\ntokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 8.29MB/s]\ntokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 8.17MB/s]",
"metrics": {
"predict_time": 12.641566,
"total_time": 125.682569
},
"output": {
"allClasses": {
"Cooking Instructions": 0.9597448110580444,
"Question about Astronomy": 0.04025513678789139
},
"mostLikelyClass": "Cooking Instructions"
},
"started_at": "2024-01-03T01:29:55.457965Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/wwjcl6rbtjkwtyy43knkb462fm",
"cancel": "https://api.replicate.com/v1/predictions/wwjcl6rbtjkwtyy43knkb462fm/cancel"
},
"version": "d929487cf059f96a17752ebe55ae5a85b2e8be6cd627078e49c6caa2fd4213db"
}Generated in
config.json: 0%| | 0.00/1.15k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.15k/1.15k [00:00<00:00, 5.85MB/s]
model.safetensors: 0%| | 0.00/1.63G [00:00<?, ?B/s]
model.safetensors: 1%| | 10.5M/1.63G [00:00<00:39, 41.3MB/s]
model.safetensors: 2%|▏ | 31.5M/1.63G [00:00<00:15, 100MB/s]
model.safetensors: 3%|▎ | 52.4M/1.63G [00:00<00:12, 129MB/s]
model.safetensors: 5%|▍ | 73.4M/1.63G [00:00<00:11, 131MB/s]
model.safetensors: 6%|▌ | 94.4M/1.63G [00:00<00:10, 140MB/s]
model.safetensors: 7%|▋ | 115M/1.63G [00:00<00:09, 158MB/s]
model.safetensors: 8%|▊ | 136M/1.63G [00:00<00:08, 169MB/s]
model.safetensors: 10%|▉ | 157M/1.63G [00:01<00:08, 167MB/s]
model.safetensors: 11%|█ | 178M/1.63G [00:01<00:08, 178MB/s]
model.safetensors: 12%|█▏ | 199M/1.63G [00:01<00:08, 177MB/s]
model.safetensors: 14%|█▎ | 220M/1.63G [00:01<00:07, 183MB/s]
model.safetensors: 15%|█▍ | 241M/1.63G [00:01<00:07, 186MB/s]
model.safetensors: 16%|█▌ | 262M/1.63G [00:01<00:07, 189MB/s]
model.safetensors: 17%|█▋ | 283M/1.63G [00:01<00:06, 193MB/s]
model.safetensors: 19%|█▉ | 315M/1.63G [00:01<00:06, 199MB/s]
model.safetensors: 21%|██ | 336M/1.63G [00:02<00:06, 198MB/s]
model.safetensors: 22%|██▏ | 357M/1.63G [00:02<00:06, 200MB/s]
model.safetensors: 23%|██▎ | 377M/1.63G [00:02<00:06, 197MB/s]
model.safetensors: 24%|██▍ | 398M/1.63G [00:02<00:06, 197MB/s]
model.safetensors: 26%|██▋ | 430M/1.63G [00:02<00:05, 202MB/s]
model.safetensors: 28%|██▊ | 461M/1.63G [00:02<00:05, 206MB/s]
model.safetensors: 30%|███ | 493M/1.63G [00:02<00:05, 209MB/s]
model.safetensors: 32%|███▏ | 524M/1.63G [00:02<00:05, 208MB/s]
model.safetensors: 33%|███▎ | 545M/1.63G [00:03<00:05, 206MB/s]
model.safetensors: 35%|███▍ | 566M/1.63G [00:03<00:05, 203MB/s]
model.safetensors: 36%|███▌ | 587M/1.63G [00:03<00:05, 202MB/s]
model.safetensors: 37%|███▋ | 608M/1.63G [00:03<00:05, 202MB/s]
model.safetensors: 39%|███▊ | 629M/1.63G [00:03<00:04, 203MB/s]
model.safetensors: 41%|████ | 661M/1.63G [00:03<00:04, 206MB/s]
model.safetensors: 42%|████▏ | 682M/1.63G [00:03<00:04, 205MB/s]
model.safetensors: 43%|████▎ | 703M/1.63G [00:03<00:04, 203MB/s]
model.safetensors: 44%|████▍ | 724M/1.63G [00:03<00:05, 178MB/s]
model.safetensors: 46%|████▌ | 744M/1.63G [00:04<00:04, 186MB/s]
model.safetensors: 48%|████▊ | 776M/1.63G [00:04<00:04, 193MB/s]
model.safetensors: 49%|████▉ | 797M/1.63G [00:04<00:04, 195MB/s]
model.safetensors: 50%|█████ | 818M/1.63G [00:04<00:04, 198MB/s]
model.safetensors: 52%|█████▏ | 849M/1.63G [00:04<00:03, 203MB/s]
model.safetensors: 54%|█████▍ | 881M/1.63G [00:04<00:03, 201MB/s]
model.safetensors: 55%|█████▌ | 902M/1.63G [00:04<00:03, 200MB/s]
model.safetensors: 57%|█████▋ | 923M/1.63G [00:04<00:03, 199MB/s]
model.safetensors: 58%|█████▊ | 944M/1.63G [00:05<00:03, 202MB/s]
model.safetensors: 60%|█████▉ | 975M/1.63G [00:05<00:03, 204MB/s]
model.safetensors: 61%|██████ | 996M/1.63G [00:05<00:03, 204MB/s]
model.safetensors: 62%|██████▏ | 1.02G/1.63G [00:05<00:03, 200MB/s]
model.safetensors: 64%|██████▎ | 1.04G/1.63G [00:05<00:02, 200MB/s]
model.safetensors: 66%|██████▌ | 1.07G/1.63G [00:05<00:02, 205MB/s]
model.safetensors: 67%|██████▋ | 1.09G/1.63G [00:05<00:02, 191MB/s]
model.safetensors: 69%|██████▉ | 1.12G/1.63G [00:05<00:02, 199MB/s]
model.safetensors: 70%|███████ | 1.14G/1.63G [00:06<00:02, 200MB/s]
model.safetensors: 71%|███████▏ | 1.16G/1.63G [00:06<00:02, 201MB/s]
model.safetensors: 73%|███████▎ | 1.18G/1.63G [00:06<00:02, 204MB/s]
model.safetensors: 75%|███████▍ | 1.22G/1.63G [00:06<00:01, 207MB/s]
model.safetensors: 77%|███████▋ | 1.25G/1.63G [00:06<00:01, 209MB/s]
model.safetensors: 78%|███████▊ | 1.27G/1.63G [00:06<00:01, 182MB/s]
model.safetensors: 79%|███████▉ | 1.29G/1.63G [00:06<00:01, 185MB/s]
model.safetensors: 80%|████████ | 1.31G/1.63G [00:06<00:01, 172MB/s]
model.safetensors: 82%|████████▏ | 1.33G/1.63G [00:07<00:01, 176MB/s]
model.safetensors: 83%|████████▎ | 1.35G/1.63G [00:07<00:01, 183MB/s]
model.safetensors: 84%|████████▍ | 1.37G/1.63G [00:07<00:01, 189MB/s]
model.safetensors: 86%|████████▌ | 1.41G/1.63G [00:07<00:01, 198MB/s]
model.safetensors: 88%|████████▊ | 1.44G/1.63G [00:07<00:01, 192MB/s]
model.safetensors: 90%|█████████ | 1.47G/1.63G [00:07<00:00, 197MB/s]
model.safetensors: 91%|█████████▏| 1.49G/1.63G [00:07<00:00, 199MB/s]
model.safetensors: 93%|█████████▎| 1.51G/1.63G [00:07<00:00, 189MB/s]
model.safetensors: 94%|█████████▍| 1.53G/1.63G [00:08<00:00, 189MB/s]
model.safetensors: 95%|█████████▌| 1.55G/1.63G [00:08<00:00, 193MB/s]
model.safetensors: 97%|█████████▋| 1.57G/1.63G [00:08<00:00, 178MB/s]
model.safetensors: 98%|█████████▊| 1.59G/1.63G [00:08<00:00, 185MB/s]
model.safetensors: 99%|█████████▉| 1.61G/1.63G [00:08<00:00, 170MB/s]
model.safetensors: 100%|██████████| 1.63G/1.63G [00:08<00:00, 186MB/s]
tokenizer_config.json: 0%| | 0.00/26.0 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 26.0/26.0 [00:00<00:00, 78.8kB/s]
vocab.json: 0%| | 0.00/899k [00:00<?, ?B/s]
vocab.json: 100%|██████████| 899k/899k [00:00<00:00, 9.29MB/s]
merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s]
merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 61.4MB/s]
tokenizer.json: 0%| | 0.00/1.36M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 8.29MB/s]
tokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 8.17MB/s]Run time and cost
This model costs approximately $0.00058 to run on Replicate, or 1724 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 3 seconds.