Instructions to use Akajackson/synth_pass_open with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Akajackson/synth_pass_open with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Akajackson/synth_pass_open")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Akajackson/synth_pass_open") model = AutoModelForMultimodalLM.from_pretrained("Akajackson/synth_pass_open", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Akajackson/synth_pass_open with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Akajackson/synth_pass_open" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Akajackson/synth_pass_open", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Akajackson/synth_pass_open
- SGLang
How to use Akajackson/synth_pass_open 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 "Akajackson/synth_pass_open" \ --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": "Akajackson/synth_pass_open", "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 "Akajackson/synth_pass_open" \ --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": "Akajackson/synth_pass_open", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Akajackson/synth_pass_open with Docker Model Runner:
docker model run hf.co/Akajackson/synth_pass_open
Commit History
-
Training in progress, epoch 9
b0676ab -
Training in progress, epoch 9
c001a68 -
Training in progress, epoch 8
71c0baf -
Training in progress, epoch 8
5d11e66 -
Training in progress, epoch 7
ac8e50d -
Training in progress, epoch 7
ff11b0e -
Training in progress, epoch 6
1f71a16 -
Training in progress, epoch 6
07d8c07 -
Training in progress, epoch 5
0690d9a -
Training in progress, epoch 5
22fd0fb -
Training in progress, epoch 4
cd67644 -
Training in progress, epoch 4
08d07ae -
Training in progress, epoch 2
79d3659 -
Training in progress, epoch 2
09df542 -
Training in progress, epoch 1
2b8523a -
Training in progress, epoch 1
da261da -
Training in progress, epoch 0
289b4e9 -
Training in progress, epoch 0
862d120 -
Training in progress, epoch 0
4be42b9 -
Training in progress, epoch 0
9b79c22 -
initial commit
4ed15b0