Instructions to use keisoft/pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use keisoft/pretrain with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="keisoft/pretrain")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("keisoft/pretrain") model = AutoModelForCausalLM.from_pretrained("keisoft/pretrain", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use keisoft/pretrain with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "keisoft/pretrain" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "keisoft/pretrain", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/keisoft/pretrain
- SGLang
How to use keisoft/pretrain 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 "keisoft/pretrain" \ --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": "keisoft/pretrain", "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 "keisoft/pretrain" \ --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": "keisoft/pretrain", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use keisoft/pretrain with Docker Model Runner:
docker model run hf.co/keisoft/pretrain
Commit History
-
Upload model
Verified signature7a1bfdd -
Upload model
Verified signaturefbc667c -
Upload model
Verified signaturefd4ad68 -
Upload model
Verified signature07e3c04 -
Upload model
Verified signaturecaf5688 -
Upload model
Verified signature22a8f83 -
Upload model
Verified signature0407fe2 -
Upload model
Verified signatureb84d4b8 -
Upload model
Verified signature5718f49 -
Upload model
Verified signature42ed2ee -
Upload model
Verified signature5d7d4c3 -
Upload model
Verified signatureb7c2e86 -
Upload model
Verified signature78dc6ea -
Upload model
Verified signature84752ed -
Upload model
Verified signaturea97ae64 -
Upload model
Verified signature34fe5a4 -
Upload model
Verified signature5f0285c -
Upload model
Verified signature09af753 -
Upload model
Verified signature4a8221c -
Upload model
Verified signaturec9dadcd -
Upload model
Verified signature2d304d3 -
Upload model
Verified signaturea8d0469 -
Upload model
Verified signature0cea91b -
Upload model
Verified signature8b92a0d
-
Upload model
Verified signaturefd76b44
-
initial commit
2db829b