Instructions to use DebateLabKIT/cript with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DebateLabKIT/cript with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DebateLabKIT/cript")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DebateLabKIT/cript") model = AutoModelForCausalLM.from_pretrained("DebateLabKIT/cript", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DebateLabKIT/cript with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DebateLabKIT/cript" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DebateLabKIT/cript", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DebateLabKIT/cript
- SGLang
How to use DebateLabKIT/cript 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 "DebateLabKIT/cript" \ --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": "DebateLabKIT/cript", "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 "DebateLabKIT/cript" \ --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": "DebateLabKIT/cript", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DebateLabKIT/cript with Docker Model Runner:
docker model run hf.co/DebateLabKIT/cript
|
Download README.md from DebateLabKIT/cript: direct link, hf CLI and curl.
- Browser
- Download file 465 Bytes
-
https://huggingface.co/DebateLabKIT/cript/resolve/0fb13b2fd4f7ffcbf7fed262921e159466a0a813/README.md
- Command line
-
hf download hf://DebateLabKIT/cript@0fb13b2fd4f7ffcbf7fed262921e159466a0a813/README.md
-
curl -L -o README.md https://huggingface.co/DebateLabKIT/cript/resolve/0fb13b2fd4f7ffcbf7fed262921e159466a0a813/README.md
465 Bytes
metadata
language: en
tags:
- gpt2
CRiPT Model (Critical Thinking Intermediarily Pretrained Transformer)
Base version of the trained model (GPT2 architecture) presented in the paper "Critical Thinking for Language Models" (Betz, Richardson and Voigt 2020). See also: