Instructions to use haoranxu/ALMA-13B-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use haoranxu/ALMA-13B-R with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="haoranxu/ALMA-13B-R")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("haoranxu/ALMA-13B-R") model = AutoModelForCausalLM.from_pretrained("haoranxu/ALMA-13B-R") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use haoranxu/ALMA-13B-R with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "haoranxu/ALMA-13B-R" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "haoranxu/ALMA-13B-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/haoranxu/ALMA-13B-R
- SGLang
How to use haoranxu/ALMA-13B-R 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 "haoranxu/ALMA-13B-R" \ --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": "haoranxu/ALMA-13B-R", "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 "haoranxu/ALMA-13B-R" \ --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": "haoranxu/ALMA-13B-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use haoranxu/ALMA-13B-R with Docker Model Runner:
docker model run hf.co/haoranxu/ALMA-13B-R
English to Canadian French
Hi, I am working on converting the text from English to Canadian french. If I fine-tune 13B model with english to canadian french dataset, what is the possibility of effective translation?
Hi, thanks for the interest in our work!
My suggestion would be firstly trying fine-tuning on Canadian French monolingual data (not necessary to be large, maybe 500K or 1B tokens), and then fine-tune on your en->Canadian fr. I guess it would be very possible to have effective translations.
Thank you for prompt response.
Unfortunately, i have canadian french dataset, but its 60k, but i am not sure the about the diversity of those tokens after tokenizing.