Instructions to use BangorAI/ALMA-7B-Pretrain-Cy-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BangorAI/ALMA-7B-Pretrain-Cy-1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="BangorAI/ALMA-7B-Pretrain-Cy-1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BangorAI/ALMA-7B-Pretrain-Cy-1")
model = AutoModelForCausalLM.from_pretrained("BangorAI/ALMA-7B-Pretrain-Cy-1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BangorAI/ALMA-7B-Pretrain-Cy-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BangorAI/ALMA-7B-Pretrain-Cy-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BangorAI/ALMA-7B-Pretrain-Cy-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BangorAI/ALMA-7B-Pretrain-Cy-1

SGLang

How to use BangorAI/ALMA-7B-Pretrain-Cy-1 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 "BangorAI/ALMA-7B-Pretrain-Cy-1" \
    --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": "BangorAI/ALMA-7B-Pretrain-Cy-1",
		"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 "BangorAI/ALMA-7B-Pretrain-Cy-1" \
        --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": "BangorAI/ALMA-7B-Pretrain-Cy-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BangorAI/ALMA-7B-Pretrain-Cy-1 with Docker Model Runner:
```
docker model run hf.co/BangorAI/ALMA-7B-Pretrain-Cy-1
```

ALMA (Advanced Language Model-based trAnslator) is an LLM-based translation model, which adopts a new translation model paradigm: it begins with fine-tuning on monolingual data and is further optimized using high-quality parallel data. This two-step fine-tuning process ensures strong translation performance. Please find more details in the ALMA paper and in their models

@misc{xu2023paradigm,
      title={A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models}, 
      author={Haoran Xu and Young Jin Kim and Amr Sharaf and Hany Hassan Awadalla},
      year={2023},
      eprint={2309.11674},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

This is a release of a Full-weight Fine-tune LLaMA-2-7b on the Welsh OSCAR-2301 dataset. It should be used to further fine-tune on either human-written parallal data for a translation model, or other chat or instruct datasets in Welsh for research.

Downloads last month: 7

Paper for BangorAI/ALMA-7B-Pretrain-Cy-1

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

Paper • 2309.11674 • Published Sep 20, 2023 • 33