Instructions to use Vyk223/model_output with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vyk223/model_output with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Vyk223/model_output")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Vyk223/model_output") model = AutoModelForMultimodalLM.from_pretrained("Vyk223/model_output") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Vyk223/model_output with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Vyk223/model_output" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Vyk223/model_output", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Vyk223/model_output
- SGLang
How to use Vyk223/model_output 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 "Vyk223/model_output" \ --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": "Vyk223/model_output", "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 "Vyk223/model_output" \ --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": "Vyk223/model_output", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Vyk223/model_output with Docker Model Runner:
docker model run hf.co/Vyk223/model_output
Vyk223/distilgpt2-summarizer
Browse files
README.md
CHANGED
|
@@ -55,5 +55,5 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
- Transformers 5.6.2
|
| 57 |
- Pytorch 2.11.0+cu130
|
| 58 |
-
- Datasets 4.8.
|
| 59 |
- Tokenizers 0.22.2
|
|
|
|
| 55 |
|
| 56 |
- Transformers 5.6.2
|
| 57 |
- Pytorch 2.11.0+cu130
|
| 58 |
+
- Datasets 4.8.5
|
| 59 |
- Tokenizers 0.22.2
|