Instructions to use instruction-pretrain/InstructLM-500M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use instruction-pretrain/InstructLM-500M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="instruction-pretrain/InstructLM-500M")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("instruction-pretrain/InstructLM-500M") model = AutoModelForCausalLM.from_pretrained("instruction-pretrain/InstructLM-500M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use instruction-pretrain/InstructLM-500M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "instruction-pretrain/InstructLM-500M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "instruction-pretrain/InstructLM-500M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/instruction-pretrain/InstructLM-500M
- SGLang
How to use instruction-pretrain/InstructLM-500M 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 "instruction-pretrain/InstructLM-500M" \ --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": "instruction-pretrain/InstructLM-500M", "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 "instruction-pretrain/InstructLM-500M" \ --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": "instruction-pretrain/InstructLM-500M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use instruction-pretrain/InstructLM-500M with Docker Model Runner:
docker model run hf.co/instruction-pretrain/InstructLM-500M
Commit History
-
Update README.md
Verified signature2158022
-
Update README.md
Verified signatureee0729f -
Update README.md
Verified signatured2fdf23
-
Update README.md
Verified signature6488600
-
Update README.md
Verified signature1238d85
-
Update README.md
Verified signature599cfe6
-
Update README.md
Verified signaturee1de99c
-
Adding `safetensors` variant of this model (#1)
Verified signature- Adding `safetensors` variant of this model (7d4277d59a909f69a3543f42810a5f9b3f9adbd4) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>de2f422
-
Update README.md
Verified signature91e79c7 -
Update README.md
Verified signature996f824
-
Update README.md
Verified signature21cd91a
-
Update README.md
Verified signaturebbcfb36
-
Update README.md
Verified signaturedb13bd2
-
Update README.md
Verified signature37c4b64
-
Update README.md
Verified signaturee9d3382
-
Update README.md
Verified signature935d41e
-
Update README.md
Verified signaturecd3fa9c -
Update README.md
Verified signature2ae20f7
-
Update README.md
Verified signature52481bb -
Update README.md
Verified signature0af297c -
Update README.md
Verified signature9feb0cd -
Update README.md
Verified signature8a5e3ac -
Upload 8 files
Verified signature6bcbd8a
-
initial commit
Verified signatured916a1f