Introducing BEREL: BERT Embeddings for Rabbinic-Encoded Language
Paper โข 2208.01875 โข Published โข 1
How to use dicta-il/BEREL_3.0 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="dicta-il/BEREL_3.0") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("dicta-il/BEREL_3.0")
model = AutoModelForCausalLM.from_pretrained("dicta-il/BEREL_3.0")How to use dicta-il/BEREL_3.0 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dicta-il/BEREL_3.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "dicta-il/BEREL_3.0",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/dicta-il/BEREL_3.0
How to use dicta-il/BEREL_3.0 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "dicta-il/BEREL_3.0" \
--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": "dicta-il/BEREL_3.0",
"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 "dicta-il/BEREL_3.0" \
--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": "dicta-il/BEREL_3.0",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use dicta-il/BEREL_3.0 with Docker Model Runner:
docker model run hf.co/dicta-il/BEREL_3.0
When using BEREL 3.0, please reference:
Avi Shmidman, Joshua Guedalia, Shaltiel Shmidman, Cheyn Shmuel Shmidman, Eli Handel, Moshe Koppel, "Introducing BEREL: BERT Embeddings for Rabbinic-Encoded Language", Aug 2022 [arXiv:2208.01875]
from transformers import AutoTokenizer, BertForMaskedLM
tokenizer = AutoTokenizer.from_pretrained('dicta-il/BEREL_3.0')
model = BertForMaskedLM.from_pretrained('dicta-il/BEREL_3.0')
# for evaluation, disable dropout
model.eval()
NOTE: This code will not work and provide bad results if you use
BertTokenizer. Please useAutoTokenizerorBertTokenizerFast.