Prediction
mistralai/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70ID
quh3kf3b23ftbag2dvjtebysfy
Status
Succeeded
Source
Web
Hardware
A40 (Large)
Total duration
Created
by @jakedahn
Input
- debug
- top_k
- 50
- top_p
- 0.9
- prompt
- [INST] Given the following JSON weather data, write a weather report: { "location": "San Francisco, CA", "temperature: "65ºF", "forecast_high": "81ºF", "forecast_low": "63ºF" "time": "2023-10-09 10:00" } You must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data. All responses must sound like a human meteorologist. [/INST]
- temperature
- 0.7
- max_new_tokens
- 500
- min_new_tokens
- -1
{
"debug": false,
"top_k": 50,
"top_p": 0.9,
"prompt": "[INST]\nGiven the following JSON weather data, write a weather report: \n\n{\n \"location\": \"San Francisco, CA\",\n \"temperature: \"65ºF\",\n \"forecast_high\": \"81ºF\",\n \"forecast_low\": \"63ºF\"\n \"time\": \"2023-10-09 10:00\"\n}\n\nYou must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.\n\nAll responses must sound like a human meteorologist.\n\n[/INST]",
"temperature": 0.7,
"max_new_tokens": 500,
"min_new_tokens": -1
}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 mistralai/mistral-7b-instruct-v0.1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"mistralai/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70",
{
input: {
debug: false,
top_k: 50,
top_p: 0.9,
prompt: "[INST]\nGiven the following JSON weather data, write a weather report: \n\n{\n \"location\": \"San Francisco, CA\",\n \"temperature: \"65ºF\",\n \"forecast_high\": \"81ºF\",\n \"forecast_low\": \"63ºF\"\n \"time\": \"2023-10-09 10:00\"\n}\n\nYou must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.\n\nAll responses must sound like a human meteorologist.\n\n[/INST]",
temperature: 0.7,
max_new_tokens: 500,
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 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 mistralai/mistral-7b-instruct-v0.1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"mistralai/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70",
input={
"debug": False,
"top_k": 50,
"top_p": 0.9,
"prompt": "[INST]\nGiven the following JSON weather data, write a weather report: \n\n{\n \"location\": \"San Francisco, CA\",\n \"temperature: \"65ºF\",\n \"forecast_high\": \"81ºF\",\n \"forecast_low\": \"63ºF\"\n \"time\": \"2023-10-09 10:00\"\n}\n\nYou must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.\n\nAll responses must sound like a human meteorologist.\n\n[/INST]",
"temperature": 0.7,
"max_new_tokens": 500,
"min_new_tokens": -1
}
)
# The mistralai/mistral-7b-instruct-v0.1 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/mistralai/mistral-7b-instruct-v0.1/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 mistralai/mistral-7b-instruct-v0.1 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": "mistralai/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70",
"input": {
"debug": false,
"top_k": 50,
"top_p": 0.9,
"prompt": "[INST]\\nGiven the following JSON weather data, write a weather report: \\n\\n{\\n \\"location\\": \\"San Francisco, CA\\",\\n \\"temperature: \\"65ºF\\",\\n \\"forecast_high\\": \\"81ºF\\",\\n \\"forecast_low\\": \\"63ºF\\"\\n \\"time\\": \\"2023-10-09 10:00\\"\\n}\\n\\nYou must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.\\n\\nAll responses must sound like a human meteorologist.\\n\\n[/INST]",
"temperature": 0.7,
"max_new_tokens": 500,
"min_new_tokens": -1
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
Good morning! Today in San Francisco, CA, the temperature is currently 65 degrees Fahrenheit. The forecast for the day calls for a high of 81 degrees and a low of 63 degrees. It's a beautiful day to explore the city and enjoy the outdoors. Make sure to stay hydrated and wear sunscreen if you plan on spending time in the sun. Have a great day!
{
"completed_at": "2023-10-09T22:24:20.548956Z",
"created_at": "2023-10-09T22:24:14.366475Z",
"data_removed": false,
"error": null,
"id": "quh3kf3b23ftbag2dvjtebysfy",
"input": {
"debug": false,
"top_k": 50,
"top_p": 0.9,
"prompt": "[INST]\nGiven the following JSON weather data, write a weather report: \n\n{\n \"location\": \"San Francisco, CA\",\n \"temperature: \"65ºF\",\n \"forecast_high\": \"81ºF\",\n \"forecast_low\": \"63ºF\"\n \"time\": \"2023-10-09 10:00\"\n}\n\nYou must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.\n\nAll responses must sound like a human meteorologist.\n\n[/INST]",
"temperature": 0.7,
"max_new_tokens": 500,
"min_new_tokens": -1
},
"logs": "Your formatted prompt is:\n[INST] [INST]\nGiven the following JSON weather data, write a weather report:\n{\n\"location\": \"San Francisco, CA\",\n\"temperature: \"65ºF\",\n\"forecast_high\": \"81ºF\",\n\"forecast_low\": \"63ºF\"\n\"time\": \"2023-10-09 10:00\"\n}\nYou must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.\nAll responses must sound like a human meteorologist. [/INST]\nDisabling loras\nNo loras were ever loaded, nothing to disable.\nNot using LoRA\nTokens: tensor([[ 1, 733, 16289, 28793, 733, 16289, 28793, 13, 28777, 5067,\n272, 2296, 9292, 8086, 1178, 28725, 3324, 264, 8086, 2264,\n28747, 28705, 13, 13, 28751, 13, 28705, 345, 2733, 1264,\n345, 17904, 9686, 28725, 9461, 548, 13, 28705, 345, 28707,\n16561, 28747, 345, 28784, 28782, 28936, 28765, 548, 13, 28705,\n345, 994, 2867, 28730, 9301, 1264, 345, 28783, 28740, 28936,\n28765, 548, 13, 28705, 345, 994, 2867, 28730, 9381, 1264,\n345, 28784, 28770, 28936, 28765, 28739, 13, 28705, 345, 1536,\n1264, 345, 28750, 28734, 28750, 28770, 28733, 28740, 28734, 28733,\n28734, 28774, 28705, 28740, 28734, 28747, 28734, 28734, 28739, 13,\n28752, 13, 13, 1976, 1580, 865, 2264, 356, 272, 1178,\n369, 349, 3857, 297, 272, 9292, 28723, 2378, 459, 4389,\n707, 8086, 4162, 369, 460, 3536, 272, 8593, 302, 272,\n3857, 9292, 568, 2378, 459, 4389, 272, 9292, 2758, 1178,\n28723, 13, 13, 2595, 14915, 1580, 2622, 737, 264, 2930,\n1424, 28706, 271, 12418, 28723, 733, 28748, 16289, 28793]],\ndevice='cuda:0')\nThe attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\nSetting `pad_token_id` to `eos_token_id`:2 for open-end generation.\nhostname: model-83b6a56e-94fe09a4acfa2b19-gpu-a40-555b6fdf4f-9kdqv",
"metrics": {
"predict_time": 6.144503,
"total_time": 6.182481
},
"output": [
"",
"Good ",
"",
"morning! ",
"Today ",
"in ",
"San ",
"",
"Francisco, ",
"",
"CA, ",
"the ",
"temperature ",
"is ",
"currently ",
"",
"",
"65 ",
"degrees ",
"",
"",
"",
"Fahrenheit. ",
"The ",
"forecast ",
"for ",
"the ",
"day ",
"calls ",
"for ",
"a ",
"high ",
"of ",
"",
"",
"81 ",
"degrees ",
"and ",
"a ",
"low ",
"of ",
"",
"",
"63 ",
"",
"degrees. ",
"",
"",
"It's ",
"a ",
"beautiful ",
"day ",
"to ",
"explore ",
"the ",
"city ",
"and ",
"enjoy ",
"the ",
"",
"",
"outdoors. ",
"Make ",
"sure ",
"to ",
"stay ",
"",
"",
"hydrated ",
"and ",
"wear ",
"",
"sunscreen ",
"if ",
"you ",
"plan ",
"on ",
"spending ",
"time ",
"in ",
"the ",
"",
"sun. ",
"Have ",
"a ",
"great ",
"",
"",
"day!"
],
"started_at": "2023-10-09T22:24:14.404453Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/quh3kf3b23ftbag2dvjtebysfy",
"cancel": "https://api.replicate.com/v1/predictions/quh3kf3b23ftbag2dvjtebysfy/cancel"
},
"version": "83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70"
}Generated in
Your formatted prompt is:
[INST] [INST]
Given the following JSON weather data, write a weather report:
{
"location": "San Francisco, CA",
"temperature: "65ºF",
"forecast_high": "81ºF",
"forecast_low": "63ºF"
"time": "2023-10-09 10:00"
}
You must only report on the data that is provided in the JSON. Do not mention any weather details that are outside the scope of the provided JSON.. Do not mention the JSON context data.
All responses must sound like a human meteorologist. [/INST]
Disabling loras
No loras were ever loaded, nothing to disable.
Not using LoRA
Tokens: tensor([[ 1, 733, 16289, 28793, 733, 16289, 28793, 13, 28777, 5067,
272, 2296, 9292, 8086, 1178, 28725, 3324, 264, 8086, 2264,
28747, 28705, 13, 13, 28751, 13, 28705, 345, 2733, 1264,
345, 17904, 9686, 28725, 9461, 548, 13, 28705, 345, 28707,
16561, 28747, 345, 28784, 28782, 28936, 28765, 548, 13, 28705,
345, 994, 2867, 28730, 9301, 1264, 345, 28783, 28740, 28936,
28765, 548, 13, 28705, 345, 994, 2867, 28730, 9381, 1264,
345, 28784, 28770, 28936, 28765, 28739, 13, 28705, 345, 1536,
1264, 345, 28750, 28734, 28750, 28770, 28733, 28740, 28734, 28733,
28734, 28774, 28705, 28740, 28734, 28747, 28734, 28734, 28739, 13,
28752, 13, 13, 1976, 1580, 865, 2264, 356, 272, 1178,
369, 349, 3857, 297, 272, 9292, 28723, 2378, 459, 4389,
707, 8086, 4162, 369, 460, 3536, 272, 8593, 302, 272,
3857, 9292, 568, 2378, 459, 4389, 272, 9292, 2758, 1178,
28723, 13, 13, 2595, 14915, 1580, 2622, 737, 264, 2930,
1424, 28706, 271, 12418, 28723, 733, 28748, 16289, 28793]],
device='cuda:0')
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.
hostname: model-83b6a56e-94fe09a4acfa2b19-gpu-a40-555b6fdf4f-9kdqv