Text Generation
Transformers
PyTorch
Graphcore
gpt2
Generated from Trainer
text-generation-inference
Instructions to use Payoto/gpt2-finetuned-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Payoto/gpt2-finetuned-wikitext2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Payoto/gpt2-finetuned-wikitext2")# Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("Payoto/gpt2-finetuned-wikitext2") model = AutoModelWithLMHead.from_pretrained("Payoto/gpt2-finetuned-wikitext2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Payoto/gpt2-finetuned-wikitext2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Payoto/gpt2-finetuned-wikitext2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Payoto/gpt2-finetuned-wikitext2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Payoto/gpt2-finetuned-wikitext2
- SGLang
How to use Payoto/gpt2-finetuned-wikitext2 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 "Payoto/gpt2-finetuned-wikitext2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Payoto/gpt2-finetuned-wikitext2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "Payoto/gpt2-finetuned-wikitext2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Payoto/gpt2-finetuned-wikitext2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Payoto/gpt2-finetuned-wikitext2 with Docker Model Runner:
docker model run hf.co/Payoto/gpt2-finetuned-wikitext2
| { | |
| "auto_loss_scaling": false, | |
| "device_iterations": 2, | |
| "embedding_serialization_factor": 4, | |
| "enable_half_partials": true, | |
| "executable_cache_dir": "/tmp/exe_cache/language_modeling", | |
| "execute_encoder_on_cpu_for_generation": false, | |
| "gradient_accumulation_steps": 16, | |
| "inference_device_iterations": 5, | |
| "inference_replication_factor": 1, | |
| "ipus_per_replica": 4, | |
| "layers_per_ipu": [ | |
| 0, | |
| 4, | |
| 4, | |
| 4 | |
| ], | |
| "matmul_proportion": 0.25, | |
| "optimizer_state_offchip": true, | |
| "optimum_version": "1.5.1", | |
| "output_mode": "final", | |
| "recompute_checkpoint_every_layer": true, | |
| "replicated_tensor_sharding": false, | |
| "replication_factor": 1, | |
| "seed": 42, | |
| "sharded_execution_for_inference": false, | |
| "transformers_version": "4.20.1" | |
| } | |