Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use ayh015/myLightningOPD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ayh015/myLightningOPD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ayh015/myLightningOPD") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ayh015/myLightningOPD") model = AutoModelForCausalLM.from_pretrained("ayh015/myLightningOPD", 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 ayh015/myLightningOPD with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ayh015/myLightningOPD" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ayh015/myLightningOPD", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ayh015/myLightningOPD
- SGLang
How to use ayh015/myLightningOPD 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 "ayh015/myLightningOPD" \ --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": "ayh015/myLightningOPD", "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 "ayh015/myLightningOPD" \ --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": "ayh015/myLightningOPD", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ayh015/myLightningOPD with Docker Model Runner:
docker model run hf.co/ayh015/myLightningOPD
Upload setup.py with huggingface_hub
Browse files
setup.py
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
| 2 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 3 |
+
|
| 4 |
+
import sys
|
| 5 |
+
import platform
|
| 6 |
+
|
| 7 |
+
from setuptools import find_packages, setup
|
| 8 |
+
from wheel.bdist_wheel import bdist_wheel as _bdist_wheel
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
def _fetch_requirements(path):
|
| 12 |
+
with open(path, "r") as fd:
|
| 13 |
+
return [r.strip() for r in fd.readlines() if r.strip() and not r.startswith("#")]
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
# Custom wheel class to modify the wheel name
|
| 17 |
+
class bdist_wheel(_bdist_wheel):
|
| 18 |
+
def finalize_options(self):
|
| 19 |
+
_bdist_wheel.finalize_options(self)
|
| 20 |
+
self.root_is_pure = False
|
| 21 |
+
|
| 22 |
+
def get_tag(self):
|
| 23 |
+
python_version = f"cp{sys.version_info.major}{sys.version_info.minor}"
|
| 24 |
+
abi_tag = f"{python_version}"
|
| 25 |
+
|
| 26 |
+
if platform.system() == "Linux":
|
| 27 |
+
platform_tag = "manylinux1_x86_64"
|
| 28 |
+
else:
|
| 29 |
+
platform_tag = platform.system().lower()
|
| 30 |
+
|
| 31 |
+
return python_version, abi_tag, platform_tag
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
# Setup configuration
|
| 35 |
+
setup(
|
| 36 |
+
author="slime Team",
|
| 37 |
+
name="slime",
|
| 38 |
+
version="0.1.0",
|
| 39 |
+
packages=find_packages(include=["slime*", "slime_plugins*"]),
|
| 40 |
+
include_package_data=True,
|
| 41 |
+
install_requires=_fetch_requirements("requirements.txt"),
|
| 42 |
+
extras_require={
|
| 43 |
+
"fsdp": [
|
| 44 |
+
"torch>=2.0",
|
| 45 |
+
]
|
| 46 |
+
},
|
| 47 |
+
python_requires=">=3.10",
|
| 48 |
+
classifiers=[
|
| 49 |
+
"Programming Language :: Python :: 3.10",
|
| 50 |
+
"Programming Language :: Python :: 3.11",
|
| 51 |
+
"Programming Language :: Python :: 3.12",
|
| 52 |
+
"Environment :: GPU :: NVIDIA CUDA",
|
| 53 |
+
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
| 54 |
+
"Topic :: System :: Distributed Computing",
|
| 55 |
+
],
|
| 56 |
+
cmdclass={"bdist_wheel": bdist_wheel},
|
| 57 |
+
)
|