dair-ai/emotion
Viewer • Updated • 437k • 35k • 444
How to use heegyu/gpt2-emotion with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="heegyu/gpt2-emotion") # Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM
tokenizer = AutoTokenizer.from_pretrained("heegyu/gpt2-emotion")
model = AutoModelForMultimodalLM.from_pretrained("heegyu/gpt2-emotion")How to use heegyu/gpt2-emotion with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heegyu/gpt2-emotion"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "heegyu/gpt2-emotion",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/heegyu/gpt2-emotion
How to use heegyu/gpt2-emotion with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "heegyu/gpt2-emotion" \
--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": "heegyu/gpt2-emotion",
"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 "heegyu/gpt2-emotion" \
--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": "heegyu/gpt2-emotion",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use heegyu/gpt2-emotion with Docker Model Runner:
docker model run hf.co/heegyu/gpt2-emotion
from transformers import pipeline
generator = pipeline('text-generation', 'heegyu/gpt2-emotion')
prompt = "sadness I'm so " # start token should be one of ["sadness", "joy", "love", "anger", "fear", "surprise"]
print(generator(prompt)[0]['generated_text'])
>>> sadness I'm so tired of seeing all the stupid things that i ve learned from past years that i feel like ive been so stupid and blah and then i feel like ive just wasted all my energy doing stupid shit like how i never