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: 4,760 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | <?php
use OC\ServiceUnavailableException;
use OCP\IConfig;
use OCP\Util;
/**
* 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 OCA\DAV\Connector\Sabre\ExceptionLoggerPlugin;
use OCP\App\IAppManager;
use OCP\IRequest;
use OCP\Template\ITemplateManager;
use Psr\Log\LoggerInterface;
use Sabre\DAV\Exception\ServiceUnavailable;
use Sabre\DAV\Server;
/**
* Class RemoteException
* Dummy exception class to be use locally to identify certain conditions
* Will not be logged to avoid DoS
*/
class RemoteException extends \Exception {
}
function handleException(Exception|Error $e): void {
try {
$request = \OCP\Server::get(IRequest::class);
// in case the request content type is text/xml - we assume it's a WebDAV request
$isXmlContentType = strpos($request->getHeader('Content-Type'), 'text/xml');
if ($isXmlContentType === 0) {
// fire up a simple server to properly process the exception
$server = new Server();
if (!($e instanceof RemoteException)) {
// we shall not log on RemoteException
$server->addPlugin(new ExceptionLoggerPlugin('webdav', \OCP\Server::get(LoggerInterface::class)));
}
$server->on('beforeMethod:*', function () use ($e): void {
if ($e instanceof RemoteException) {
switch ($e->getCode()) {
case 503:
throw new ServiceUnavailable($e->getMessage());
case 404:
throw new \Sabre\DAV\Exception\NotFound($e->getMessage());
}
}
$class = get_class($e);
$msg = $e->getMessage();
throw new ServiceUnavailable("$class: $msg");
});
$server->exec();
} else {
$statusCode = 500;
if ($e instanceof ServiceUnavailableException) {
$statusCode = 503;
}
if ($e instanceof RemoteException) {
// we shall not log on RemoteException
\OCP\Server::get(ITemplateManager::class)->printErrorPage($e->getMessage(), '', $e->getCode());
} else {
\OCP\Server::get(LoggerInterface::class)->error($e->getMessage(), ['app' => 'remote','exception' => $e]);
\OCP\Server::get(ITemplateManager::class)->printExceptionErrorPage($e, $statusCode);
}
}
} catch (\Exception $e) {
\OCP\Server::get(ITemplateManager::class)->printExceptionErrorPage($e, 500);
}
}
/**
* @param string $service
* @return string
*/
function resolveService($service) {
$services = [
'webdav' => 'dav/appinfo/v1/webdav.php',
'dav' => 'dav/appinfo/v2/remote.php',
'caldav' => 'dav/appinfo/v1/caldav.php',
'calendar' => 'dav/appinfo/v1/caldav.php',
'carddav' => 'dav/appinfo/v1/carddav.php',
'contacts' => 'dav/appinfo/v1/carddav.php',
'files' => 'dav/appinfo/v1/webdav.php',
'direct' => 'dav/appinfo/v2/direct.php',
];
if (isset($services[$service])) {
return $services[$service];
}
return \OCP\Server::get(IConfig::class)->getAppValue('core', 'remote_' . $service);
}
try {
require_once __DIR__ . '/lib/base.php';
// All resources served via the DAV endpoint should have the strictest possible
// policy. Exempted from this is the SabreDAV browser plugin which overwrites
// this policy with a softer one if debug mode is enabled.
header("Content-Security-Policy: default-src 'none';");
if (Util::needUpgrade()) {
// since the behavior of apps or remotes are unpredictable during
// an upgrade, return a 503 directly
throw new RemoteException('Service unavailable', 503);
}
$request = \OCP\Server::get(IRequest::class);
$pathInfo = $request->getPathInfo();
if ($pathInfo === false || $pathInfo === '') {
throw new RemoteException('Path not found', 404);
}
if (!$pos = strpos($pathInfo, '/', 1)) {
$pos = strlen($pathInfo);
}
$service = substr($pathInfo, 1, $pos - 1);
$file = resolveService($service);
if (is_null($file)) {
throw new RemoteException('Path not found', 404);
}
$file = ltrim($file, '/');
$parts = explode('/', $file, 2);
$app = $parts[0];
// Load all required applications
\OC::$REQUESTEDAPP = $app;
$appManager = \OCP\Server::get(IAppManager::class);
$appManager->loadApps(['authentication']);
$appManager->loadApps(['extended_authentication']);
$appManager->loadApps(['filesystem', 'logging']);
switch ($app) {
case 'core':
$file = OC::$SERVERROOT . '/' . $file;
break;
default:
if (!$appManager->isEnabledForUser($app)) {
throw new RemoteException('App not installed: ' . $app);
}
$appManager->loadApp($app);
$file = $appManager->getAppPath($app) . '/' . ($parts[1] ?? '');
break;
}
$baseuri = OC::$WEBROOT . '/remote.php/' . $service . '/';
require_once $file;
} catch (Exception $ex) {
handleException($ex);
} catch (Error $e) {
handleException($e);
}
|