Text Generation
PEFT
Safetensors
Transformers
English
llama
lora
dpo
smollm2
trl
conversational
text-generation-inference
Instructions to use Subject-Emu-5259/NeuralAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Subject-Emu-5259/NeuralAI with PEFT:
Base model is not found.
- Transformers
How to use Subject-Emu-5259/NeuralAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Subject-Emu-5259/NeuralAI", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Subject-Emu-5259/NeuralAI") model = AutoModelForCausalLM.from_pretrained("Subject-Emu-5259/NeuralAI", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Subject-Emu-5259/NeuralAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Subject-Emu-5259/NeuralAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Subject-Emu-5259/NeuralAI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Subject-Emu-5259/NeuralAI
- SGLang
How to use Subject-Emu-5259/NeuralAI with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Subject-Emu-5259/NeuralAI" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Subject-Emu-5259/NeuralAI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Subject-Emu-5259/NeuralAI" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Subject-Emu-5259/NeuralAI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Subject-Emu-5259/NeuralAI with Docker Model Runner:
docker model run hf.co/Subject-Emu-5259/NeuralAI
File size: 4,126 Bytes
38b4eff | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 | <?php
declare(strict_types=1);
use OCP\IConfig;
use OCP\IURLGenerator;
use OCP\Server;
/**
* SPDX-FileCopyrightText: 2016-2024 Nextcloud GmbH and Nextcloud contributors
* SPDX-FileCopyrightText: 2016 ownCloud, Inc.
* SPDX-License-Identifier: AGPL-3.0-only
*/
require_once __DIR__ . '/lib/versioncheck.php';
use OC\Console\Application;
use OCP\AppFramework\Http\Response;
use OCP\Diagnostics\IEventLogger;
use OCP\IRequest;
use OCP\Profiler\IProfiler;
use Symfony\Component\Console\Input\ArgvInput;
use Symfony\Component\Console\Output\ConsoleOutput;
define('OC_CONSOLE', 1);
function exceptionHandler($exception) {
echo 'An unhandled exception has been thrown:' . PHP_EOL;
echo $exception;
exit(1);
}
try {
require_once __DIR__ . '/lib/base.php';
// set to run indefinitely if needed
if (strpos(@ini_get('disable_functions'), 'set_time_limit') === false) {
@set_time_limit(0);
}
if (!OC::$CLI) {
echo 'This script can be run from the command line only' . PHP_EOL;
exit(1);
}
$config = Server::get(IConfig::class);
set_exception_handler('exceptionHandler');
if (!function_exists('posix_getuid')) {
echo 'The posix extensions are required - see https://www.php.net/manual/en/book.posix.php' . PHP_EOL;
exit(1);
}
$user = posix_getuid();
$configUser = fileowner(OC::$configDir . 'config.php');
if ($user !== $configUser) {
echo 'Console has to be executed with the user that owns the file config/config.php' . PHP_EOL;
echo 'Current user id: ' . $user . PHP_EOL;
echo 'Owner id of config.php: ' . $configUser . PHP_EOL;
echo "Try adding 'sudo -u #" . $configUser . "' to the beginning of the command (without the single quotes)" . PHP_EOL;
echo "If running with 'docker exec' try adding the option '-u " . $configUser . "' to the docker command (without the single quotes)" . PHP_EOL;
exit(1);
}
$oldWorkingDir = getcwd();
if ($oldWorkingDir === false) {
echo 'This script can be run from the Nextcloud root directory only.' . PHP_EOL;
echo "Can't determine current working dir - the script will continue to work but be aware of the above fact." . PHP_EOL;
} elseif ($oldWorkingDir !== __DIR__ && !chdir(__DIR__)) {
echo 'This script can be run from the Nextcloud root directory only.' . PHP_EOL;
echo "Can't change to Nextcloud root directory." . PHP_EOL;
exit(1);
}
if (!(function_exists('pcntl_signal') && function_exists('pcntl_signal_dispatch')) && !in_array('--no-warnings', $argv)) {
echo 'The process control (PCNTL) extensions are required in case you want to interrupt long running commands - see https://www.php.net/manual/en/book.pcntl.php' . PHP_EOL;
echo "Additionally the function 'pcntl_signal' and 'pcntl_signal_dispatch' need to be enabled in your php.ini." . PHP_EOL;
}
$eventLogger = Server::get(IEventLogger::class);
$eventLogger->start('console:build_application', 'Build Application instance and load commands');
$application = Server::get(Application::class);
/* base.php will have removed eventual debug options from argv in $_SERVER */
$argv = $_SERVER['argv'];
$input = new ArgvInput($argv);
$output = new ConsoleOutput();
$application->loadCommands($input, $output);
$eventLogger->end('console:build_application');
$eventLogger->start('console:run', 'Run the command');
$application->setAutoExit(false);
$exitCode = $application->run($input);
$eventLogger->end('console:run');
$profiler = Server::get(IProfiler::class);
if ($profiler->isEnabled()) {
$eventLogger->end('runtime');
$profile = $profiler->collect(Server::get(IRequest::class), new Response());
$profile->setMethod('occ');
$profile->setUrl(implode(' ', $argv));
$profiler->saveProfile($profile);
$urlGenerator = Server::get(IURLGenerator::class);
$url = $urlGenerator->linkToRouteAbsolute('profiler.main.profiler', [
'profiler' => 'db',
'token' => $profile->getToken(),
]);
$output->getErrorOutput()->writeln('Profiler output available at ' . $url);
}
if ($exitCode > 255) {
$exitCode = 255;
}
exit($exitCode);
} catch (Exception $ex) {
exceptionHandler($ex);
} catch (Error $ex) {
exceptionHandler($ex);
}
|