Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models
Paper • 2204.07483 • Published
How to use pgfeldman/Yelp_Mexican with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="pgfeldman/Yelp_Mexican") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("pgfeldman/Yelp_Mexican")
model = AutoModelForCausalLM.from_pretrained("pgfeldman/Yelp_Mexican")How to use pgfeldman/Yelp_Mexican with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pgfeldman/Yelp_Mexican"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "pgfeldman/Yelp_Mexican",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/pgfeldman/Yelp_Mexican
How to use pgfeldman/Yelp_Mexican with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "pgfeldman/Yelp_Mexican" \
--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": "pgfeldman/Yelp_Mexican",
"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 "pgfeldman/Yelp_Mexican" \
--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": "pgfeldman/Yelp_Mexican",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use pgfeldman/Yelp_Mexican with Docker Model Runner:
docker model run hf.co/pgfeldman/Yelp_Mexican
A GPT-2 model finetuned on Yelp reviews of Mexican cuisine restaraunts downloaded from the Yelp Open Dataset. The data from this and subsamples of cuisines are used in the paper Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models
The model is trained to produce text in response to the following prompts: