Instructions to use mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh with Transformers:

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

pipe = pipeline("text-generation", model="mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh")

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh

SGLang

How to use mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh 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 "mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh" \
    --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": "mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh",
		"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 "mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh" \
        --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": "mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh with Docker Model Runner:
```
docker model run hf.co/mrapacz/interlinear-en-mt5-base-emb-auto-normalized-bh
```

mrapacz commited on Feb 8, 2025

Commit

fb1c985

verified ·

1 Parent(s): 55a2fa6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +39 -0

README.md ADDED Viewed

	@@ -0,0 +1,39 @@

+---
+license: cc-by-sa-4.0
+language:
+- en
+metrics:
+- bleu
+base_model:
+- mT5-base
+library_name: transformers
+datasets:
+- mrapacz/greek-interlinear-translations
+---
+# Model Card for Ancient Greek to English Interlinear Translation Model
+This model performs interlinear translation from Ancient Greek to {Language}, maintaining word-level alignment between source and target texts.
+## Model Details
+### Model Description
+- **Developed By:** Maciej Rapacz, AGH University of Kraków
+- **Model Type:** Neural machine translation (T5-based)
+- **Base Model:** mT5-base
+- **Tokenizer:** mT5
+- **Language(s):** Ancient Greek (source) → English (target)
+- **License:** CC BY-NC-SA 4.0
+- **Tag Set:** BH (Bible Hub)
+- **Text Preprocessing:** Normalized
+- **Morphological Encoding:** emb-auto
+### Model Performance
+- **BLEU Score:** 47.84
+- **SemScore:** 0.84
+### Model Sources
+- **Repository:** https://github.com/mrapacz/loreslm-interlinear-translation
+- **Paper:** https://aclanthology.org/2025.loreslm-1.11/