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
| # SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. | |
| # SPDX-License-Identifier: Apache-2.0 | |
| import json | |
| from pathlib import Path | |
| from types import SimpleNamespace | |
| from typing import Annotated | |
| import torch | |
| import typer | |
| from slime.ray.rollout import compute_metrics_from_samples | |
| from slime.utils.types import Sample | |
| _WHITELIST_KEYS = [ | |
| "group_index", | |
| "index", | |
| "prompt", | |
| "response", | |
| "response_length", | |
| "label", | |
| "reward", | |
| "status", | |
| "metadata", | |
| ] | |
| def main( | |
| # Deliberately make this name consistent with main training arguments | |
| load_debug_rollout_data: Annotated[str, typer.Option()], | |
| show_metrics: bool = True, | |
| show_samples: bool = True, | |
| category: list[str] = None, | |
| ): | |
| if category is None: | |
| category = ["train", "eval"] | |
| for rollout_id, path in _get_rollout_dump_paths(load_debug_rollout_data, category): | |
| print("-" * 80) | |
| print(f"{rollout_id=} {path=}") | |
| print("-" * 80) | |
| pack = torch.load(path) | |
| sample_dicts = pack["samples"] | |
| if show_metrics: | |
| # TODO read these configs from dumps | |
| args = SimpleNamespace( | |
| advantage_estimator="grpo", | |
| reward_key=None, | |
| log_reward_category=None, | |
| ) | |
| sample_objects = [Sample.from_dict(s) for s in sample_dicts] | |
| metrics = compute_metrics_from_samples(args, sample_objects) | |
| print("metrics", metrics) | |
| if show_samples: | |
| for sample in sample_dicts: | |
| print(json.dumps({k: v for k, v in sample.items() if k in _WHITELIST_KEYS})) | |
| def _get_rollout_dump_paths(load_debug_rollout_data: str, categories: list[str]): | |
| # may improve later | |
| for rollout_id in range(1000): | |
| for category in categories: | |
| prefix = { | |
| "train": "", | |
| "eval": "eval_", | |
| }[category] | |
| path = Path(load_debug_rollout_data.format(rollout_id=f"{prefix}{rollout_id}")) | |
| if path.exists(): | |
| yield rollout_id, path | |
| if __name__ == "__main__": | |
| """python -m slime.utils.debug_utils.display_debug_rollout_data --load-debug-rollout-data ...""" | |
| typer.run(main) | |