Prediction

Model

cjwbw/gorilla:4a1a7ce8

bc2uwn3btg3wvuu5tejtocsi5m

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

4m 15s

Created

about 2 years ago

Webhook

–

Input

prompt: I would like to translate 'I feel very good today.' from English to French.
model_name: gorilla-llm/gorilla-falcon-7b-hf-v0
temperature: 0.7
max_new_tokens: 1024

{
  "max_new_tokens": 1024,
  "model_name": "gorilla-llm/gorilla-falcon-7b-hf-v0",
  "prompt": "I would like to translate 'I feel very good today.' from English to French.",
  "temperature": 0.7
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_IFL**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run cjwbw/gorilla using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cjwbw/gorilla:4a1a7ce831b1315ab68a6b3ccf54bf376de787c93198a95a329582105b70e083",
  {
    input: {
      max_new_tokens: 1024,
      model_name: "gorilla-llm/gorilla-falcon-7b-hf-v0",
      prompt: "I would like to translate 'I feel very good today.' from English to French.",
      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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_IFL**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run cjwbw/gorilla using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/gorilla:4a1a7ce831b1315ab68a6b3ccf54bf376de787c93198a95a329582105b70e083",
    input={
        "max_new_tokens": 1024,
        "model_name": "gorilla-llm/gorilla-falcon-7b-hf-v0",
        "prompt": "I would like to translate 'I feel very good today.' from English to French.",
        "temperature": 0.7
    }
)

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=r8_IFL**********************************

This is your API token. Keep it to yourself.

Run cjwbw/gorilla 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": "cjwbw/gorilla:4a1a7ce831b1315ab68a6b3ccf54bf376de787c93198a95a329582105b70e083",
    "input": {
      "max_new_tokens": 1024,
      "model_name": "gorilla-llm/gorilla-falcon-7b-hf-v0",
      "prompt": "I would like to translate \'I feel very good today.\' from English to French.",
      "temperature": 0.7
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Object output with 6 properties

code_parsed

from transformers import pipeline
translator = pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')
translated_text = translator("I feel very good today.")[0]['translation_text']"

domain_parsed

Natural Language Processing Translation\n

api_call_parsed

pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\n

raw_text_response

\n<<<domain>>>: Natural Language Processing Translation\n<<<api_call>>>: pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\n<<<api_provider>>>: Hugging Face Transformers\n<<<explanation>>>: 1. We first import the pipeline function from the transformers library provided by Hugging Face.\n2. We then use the pipeline function to create a translation model.\n3. We specify the model 'Helsinki-NLP/opus-mt-en-fr' to be loaded. This model is trained for English to French translation tasks, which is exactly what we need for translating 'I feel very good today.'\n4. We can pass the English text as input and the model will return the translated French text.\n<<<code>>>: from transformers import pipeline\ntranslator = pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\ntranslated_text = translator(\"I feel very good today.\")[0]['translation_text']"

explanation_parsed

1. We first import the pipeline function from the transformers library provided by Hugging Face.
2. We then use the pipeline function to create a translation model.
3. We specify the model 'Helsinki-NLP/opus-mt-en-fr' to be loaded. This model is trained for English to French translation tasks, which is exactly what we need for translating 'I feel very good today.'n4. We can pass the English text as input and the model will return the translated French text.

api_provider_parsed

Hugging Face Transformers\n

{
  "id": "bc2uwn3btg3wvuu5tejtocsi5m",
  "model": "cjwbw/gorilla",
  "version": "4a1a7ce831b1315ab68a6b3ccf54bf376de787c93198a95a329582105b70e083",
  "input": {
    "max_new_tokens": 1024,
    "model_name": "gorilla-llm/gorilla-falcon-7b-hf-v0",
    "prompt": "I would like to translate 'I feel very good today.' from English to French.",
    "temperature": 0.7
  },
  "logs": "/root/.pyenv/versions/3.11.4/lib/python3.11/site-packages/transformers/generation/utils.py:1270: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation )\nwarnings.warn(\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`:11 for open-end generation.",
  "output": {
    "api_call_parsed": "pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\\n",
    "api_provider_parsed": "Hugging Face Transformers\\n",
    "code_parsed": "from transformers import pipeline\ntranslator = pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\ntranslated_text = translator(\"I feel very good today.\")[0]['translation_text']\"",
    "domain_parsed": "Natural Language Processing Translation\\n",
    "explanation_parsed": "1. We first import the pipeline function from the transformers library provided by Hugging Face.\n2. We then use the pipeline function to create a translation model.\n3. We specify the model 'Helsinki-NLP/opus-mt-en-fr' to be loaded. This model is trained for English to French translation tasks, which is exactly what we need for translating 'I feel very good today.'n4. We can pass the English text as input and the model will return the translated French text.\n",
    "raw_text_response": "\\n<<<domain>>>: Natural Language Processing Translation\\n<<<api_call>>>: pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\\n<<<api_provider>>>: Hugging Face Transformers\\n<<<explanation>>>: 1. We first import the pipeline function from the transformers library provided by Hugging Face.\\n2. We then use the pipeline function to create a translation model.\\n3. We specify the model 'Helsinki-NLP/opus-mt-en-fr' to be loaded. This model is trained for English to French translation tasks, which is exactly what we need for translating 'I feel very good today.'\\n4. We can pass the English text as input and the model will return the translated French text.\\n<<<code>>>: from transformers import pipeline\\ntranslator = pipeline('translation_en_to_fr', model='Helsinki-NLP/opus-mt-en-fr')\\ntranslated_text = translator(\\\"I feel very good today.\\\")[0]['translation_text']\""
  },
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2023-11-07T12:28:21.908586Z",
  "started_at": "2023-11-07T12:32:27.408314Z",
  "completed_at": "2023-11-07T12:32:36.416744Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/bc2uwn3btg3wvuu5tejtocsi5m/cancel",
    "get": "https://api.replicate.com/v1/predictions/bc2uwn3btg3wvuu5tejtocsi5m"
  },
  "metrics": {
    "predict_time": 9.00843,
    "total_time": 254.508158
  }
}

Generated in

9.0 seconds

Tweak it Report