Instructions to use mismayil/comet-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mismayil/comet-gpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mismayil/comet-gpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mismayil/comet-gpt2") model = AutoModelForCausalLM.from_pretrained("mismayil/comet-gpt2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mismayil/comet-gpt2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mismayil/comet-gpt2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mismayil/comet-gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mismayil/comet-gpt2
- SGLang
How to use mismayil/comet-gpt2 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 "mismayil/comet-gpt2" \ --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": "mismayil/comet-gpt2", "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 "mismayil/comet-gpt2" \ --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": "mismayil/comet-gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mismayil/comet-gpt2 with Docker Model Runner:
docker model run hf.co/mismayil/comet-gpt2
| {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": "[EOS]", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "[PAD]", "additional_special_tokens": ["AtLocation", "CapableOf", "Causes", "CausesDesire", "CreatedBy", "DefinedAs", "DesireOf", "Desires", "HasA", "HasFirstSubevent", "HasLastSubevent", "HasPainCharacter", "HasPainIntensity", "HasPrerequisite", "HasProperty", "HasSubEvent", "HasSubevent", "HinderedBy", "InheritsFrom", "InstanceOf", "IsA", "LocatedNear", "LocationOfAction", "MadeOf", "MadeUpOf", "MotivatedByGoal", "NotCapableOf", "NotDesires", "NotHasA", "NotHasProperty", "NotIsA", "NotMadeOf", "ObjectUse", "PartOf", "ReceivesAction", "RelatedTo", "SymbolOf", "UsedFor", "isAfter", "isBefore", "isFilledBy", "oEffect", "oReact", "oWant", "xAttr", "xEffect", "xIntent", "xNeed", "xReact", "xReason", "xWant", "[GEN]"]} |