Instructions to use James-WYang/BigTranslate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use James-WYang/BigTranslate with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="James-WYang/BigTranslate")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("James-WYang/BigTranslate") model = AutoModelForCausalLM.from_pretrained("James-WYang/BigTranslate") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use James-WYang/BigTranslate with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "James-WYang/BigTranslate" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "James-WYang/BigTranslate", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/James-WYang/BigTranslate
- SGLang
How to use James-WYang/BigTranslate 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 "James-WYang/BigTranslate" \ --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": "James-WYang/BigTranslate", "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 "James-WYang/BigTranslate" \ --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": "James-WYang/BigTranslate", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use James-WYang/BigTranslate with Docker Model Runner:
docker model run hf.co/James-WYang/BigTranslate
LLaMATokenizer renders this incompatible with huggingfaces transformers pipeline
#1
by Alignment-Lab-AI - opened
in transformers the tokenizer is listed as LlamaTokenizer
attempting to run this through any transformers based system results in an error, rendering it incompatible unless the user downloads it and renames it themselves.
i believe attempting to even download the model from huggingface throws the error, its been a bit over a week since i involved BigTrans in my research but i believe i had to wget each file link to retrieve it