Instructions to use PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token") model = AutoModelForCausalLM.from_pretrained("PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token
- SGLang
How to use PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token 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 "PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token" \ --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": "PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token", "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 "PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token" \ --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": "PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token with Docker Model Runner:
docker model run hf.co/PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token
Download tokenizer.json from PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token/resolve/main/tokenizer.json
- Command line
-
hf download hf://PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/PathFinderKR/Llama-3.2-1B-Instruct-Pause_Token/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- d7c53cfc66d7300b50300d3f9e85445545d550772b1cabd5de8d51fc9b85f830
- Size of remote file:
- 17.2 MB
- SHA256:
- c07f570a41521b4b584f0f4a1567e6de4e9cebdeaa099aaab014ae44a7f811c6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.