Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
organisciak /ocsai-llama2-7b:b00751d0
Input
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run organisciak/ocsai-llama2-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"organisciak/ocsai-llama2-7b:b00751d00cca65ff9213aea7d4fc79b9f91d2af25c5f097bd2d9fd29cc952218",
{
input: {
debug: false,
top_p: 0.95,
prompt: "AUT Prompt:brick\nResponse:build bookshelves \nScore:\n\n",
temperature: 0.01,
return_logits: false,
max_new_tokens: 128,
min_new_tokens: -1,
repetition_penalty: 1.15
}
}
);
console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run organisciak/ocsai-llama2-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"organisciak/ocsai-llama2-7b:b00751d00cca65ff9213aea7d4fc79b9f91d2af25c5f097bd2d9fd29cc952218",
input={
"debug": False,
"top_p": 0.95,
"prompt": "AUT Prompt:brick\nResponse:build bookshelves \nScore:\n\n",
"temperature": 0.01,
"return_logits": False,
"max_new_tokens": 128,
"min_new_tokens": -1,
"repetition_penalty": 1.15
}
)
# The organisciak/ocsai-llama2-7b 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/organisciak/ocsai-llama2-7b/api#output-schema
print(item, end="")
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run organisciak/ocsai-llama2-7b 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": "organisciak/ocsai-llama2-7b:b00751d00cca65ff9213aea7d4fc79b9f91d2af25c5f097bd2d9fd29cc952218",
"input": {
"debug": false,
"top_p": 0.95,
"prompt": "AUT Prompt:brick\\nResponse:build bookshelves \\nScore:\\n\\n",
"temperature": 0.01,
"return_logits": false,
"max_new_tokens": 128,
"min_new_tokens": -1,
"repetition_penalty": 1.15
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2024-01-10T18:31:56.538601Z",
"created_at": "2024-01-10T18:31:56.371419Z",
"data_removed": false,
"error": null,
"id": "fxo55flbel4ru3f4ooxtf6ei5q",
"input": {
"prompt": "AUT Prompt:brick\nResponse:build bookshelves \nScore:\n\n",
"temperature": 0.01
},
"logs": "Your formatted prompt is:\nAUT Prompt:brick\nResponse:build bookshelves\nScore:\ncorrect lora is already loaded\nOverall initialize_peft took 0.000\nExllama: False\nINFO 01-10 18:31:56 async_llm_engine.py:371] Received request 0: prompt: 'AUT Prompt:brick\\nResponse:build bookshelves \\nScore:\\n\\n', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=1.0, temperature=0.01, top_p=0.95, top_k=50, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['</s>'], ignore_eos=False, max_tokens=128, logprobs=None, skip_special_tokens=True), prompt token ids: None.\nINFO 01-10 18:31:56 async_llm_engine.py:111] Finished request 0.\nhostname: model-hs-77dde5d6-e494c37392ea209c-gpu-a40-5fcfffb44d-5wvkg",
"metrics": {
"predict_time": 0.132829,
"total_time": 0.167182
},
"output": [
"1",
"5",
""
],
"started_at": "2024-01-10T18:31:56.405772Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/fxo55flbel4ru3f4ooxtf6ei5q",
"cancel": "https://api.replicate.com/v1/predictions/fxo55flbel4ru3f4ooxtf6ei5q/cancel"
},
"version": "b00751d00cca65ff9213aea7d4fc79b9f91d2af25c5f097bd2d9fd29cc952218"
}
Your formatted prompt is:
AUT Prompt:brick
Response:build bookshelves
Score:
correct lora is already loaded
Overall initialize_peft took 0.000
Exllama: False
INFO 01-10 18:31:56 async_llm_engine.py:371] Received request 0: prompt: 'AUT Prompt:brick\nResponse:build bookshelves \nScore:\n\n', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=1.0, temperature=0.01, top_p=0.95, top_k=50, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['</s>'], ignore_eos=False, max_tokens=128, logprobs=None, skip_special_tokens=True), prompt token ids: None.
INFO 01-10 18:31:56 async_llm_engine.py:111] Finished request 0.
hostname: model-hs-77dde5d6-e494c37392ea209c-gpu-a40-5fcfffb44d-5wvkg