Instructions to use armandnlp/gpt2-EmoWOZ-SimpleToD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use armandnlp/gpt2-EmoWOZ-SimpleToD with Transformers:

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

pipe = pipeline("text-generation", model="armandnlp/gpt2-EmoWOZ-SimpleToD")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("armandnlp/gpt2-EmoWOZ-SimpleToD")
model = AutoModelForCausalLM.from_pretrained("armandnlp/gpt2-EmoWOZ-SimpleToD")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use armandnlp/gpt2-EmoWOZ-SimpleToD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "armandnlp/gpt2-EmoWOZ-SimpleToD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "armandnlp/gpt2-EmoWOZ-SimpleToD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/armandnlp/gpt2-EmoWOZ-SimpleToD

SGLang

How to use armandnlp/gpt2-EmoWOZ-SimpleToD 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 "armandnlp/gpt2-EmoWOZ-SimpleToD" \
    --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": "armandnlp/gpt2-EmoWOZ-SimpleToD",
		"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 "armandnlp/gpt2-EmoWOZ-SimpleToD" \
        --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": "armandnlp/gpt2-EmoWOZ-SimpleToD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use armandnlp/gpt2-EmoWOZ-SimpleToD with Docker Model Runner:
```
docker model run hf.co/armandnlp/gpt2-EmoWOZ-SimpleToD
```

armandnlp commited on Nov 25, 2023

Commit

f93d2a1

1 Parent(s): 221651b

Update generation_config.json

Browse files

Files changed (1) hide show

generation_config.json +1 -1

generation_config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "do_sample": false,
   "bos_token_id": 50256,
   "eos_token_id": 50262,
-  "max_length": 50,
   "no_repeat_ngram_size": 10,
   "transformers_version": "4.27.4"
 }

   "do_sample": false,
   "bos_token_id": 50256,
   "eos_token_id": 50262,
+  "max_length": 500,
   "no_repeat_ngram_size": 10,
   "transformers_version": "4.27.4"
 }