Text Generation
Transformers
TensorBoard
Safetensors
phi
Generated from Trainer
custom_code
text-generation-inference
Instructions to use iliazlobin/phi-2-coedit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iliazlobin/phi-2-coedit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="iliazlobin/phi-2-coedit", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("iliazlobin/phi-2-coedit", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("iliazlobin/phi-2-coedit", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use iliazlobin/phi-2-coedit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "iliazlobin/phi-2-coedit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "iliazlobin/phi-2-coedit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/iliazlobin/phi-2-coedit
- SGLang
How to use iliazlobin/phi-2-coedit 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 "iliazlobin/phi-2-coedit" \ --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": "iliazlobin/phi-2-coedit", "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 "iliazlobin/phi-2-coedit" \ --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": "iliazlobin/phi-2-coedit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use iliazlobin/phi-2-coedit with Docker Model Runner:
docker model run hf.co/iliazlobin/phi-2-coedit
Ctrl+K
complete: train_size: {train_size}, batch_size: {batch_size}, per_epoch_steps: {per_epoch_steps}, epochs: {epochs}, epoch_total_steps: {epoch_total_steps}
f21cbc1 verified