Instructions to use tobijen/bert_left_headings with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tobijen/bert_left_headings with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tobijen/bert_left_headings")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tobijen/bert_left_headings") model = AutoModelForCausalLM.from_pretrained("tobijen/bert_left_headings", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use tobijen/bert_left_headings with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tobijen/bert_left_headings" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tobijen/bert_left_headings", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tobijen/bert_left_headings
- SGLang
How to use tobijen/bert_left_headings 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 "tobijen/bert_left_headings" \ --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": "tobijen/bert_left_headings", "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 "tobijen/bert_left_headings" \ --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": "tobijen/bert_left_headings", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tobijen/bert_left_headings with Docker Model Runner:
docker model run hf.co/tobijen/bert_left_headings
Commit History
-
Training in progress epoch 5
0565ed8 -
Training in progress epoch 4
068e48b -
Training in progress epoch 3
994cb79 -
Training in progress epoch 2
eaedbb8 -
Training in progress epoch 1
c9e717d -
Training in progress epoch 0
2622f58 -
Training in progress epoch 4
f10b76b -
Training in progress epoch 3
0500322 -
Training in progress epoch 2
bafbc8f -
Training in progress epoch 1
689d5fe -
Training in progress epoch 0
2c45abf -
Training in progress epoch 7
d88eaa7 -
Training in progress epoch 6
4443686 -
Training in progress epoch 5
b59256f -
Training in progress epoch 4
21a1f91 -
Training in progress epoch 3
bff9450 -
Training in progress epoch 2
cab4ec5 -
Training in progress epoch 1
74414d8 -
Training in progress epoch 0
a271227 -
Training in progress epoch 5
e29378a -
Training in progress epoch 4
7b11ae8 -
Training in progress epoch 3
136db39 -
Training in progress epoch 2
b186de3 -
Training in progress epoch 1
d3e4ecd -
Training in progress epoch 0
6accec5
-
Training in progress epoch 5
3f9fe59 -
Training in progress epoch 4
ad2cd03 -
Training in progress epoch 3
260ecfc -
Training in progress epoch 2
bf0a0a1 -
Training in progress epoch 1
3f70155 -
Training in progress epoch 0
001c979 -
initial commit
105ca8f