How to use Xwin-LM/XwinCoder-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Xwin-LM/XwinCoder-13B")
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/XwinCoder-13B") model = AutoModelForCausalLM.from_pretrained("Xwin-LM/XwinCoder-13B")
How to use Xwin-LM/XwinCoder-13B with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Xwin-LM/XwinCoder-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Xwin-LM/XwinCoder-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
docker model run hf.co/Xwin-LM/XwinCoder-13B
How to use Xwin-LM/XwinCoder-13B with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Xwin-LM/XwinCoder-13B" \ --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": "Xwin-LM/XwinCoder-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
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 "Xwin-LM/XwinCoder-13B" \ --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": "Xwin-LM/XwinCoder-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
How to use Xwin-LM/XwinCoder-13B with Docker Model Runner:
I noticed the model card is focusing heavily on the 34B model instead of the 13B model it should be focusing on. the big circular chart doesn't even include the 13B model. This was likely a bad copy and paste job.
· Sign up or log in to comment
