Instructions to use OscarNav/dialoGPT_translate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OscarNav/dialoGPT_translate with Transformers:

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

pipe = pipeline("text-generation", model="OscarNav/dialoGPT_translate")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OscarNav/dialoGPT_translate")
model = AutoModelForCausalLM.from_pretrained("OscarNav/dialoGPT_translate")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OscarNav/dialoGPT_translate with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OscarNav/dialoGPT_translate

SGLang

How to use OscarNav/dialoGPT_translate 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 "OscarNav/dialoGPT_translate" \
    --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": "OscarNav/dialoGPT_translate",
		"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 "OscarNav/dialoGPT_translate" \
        --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": "OscarNav/dialoGPT_translate",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OscarNav/dialoGPT_translate with Docker Model Runner:
```
docker model run hf.co/OscarNav/dialoGPT_translate
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Finetuned DialoGPT model for Eng-Spa translation

DialoGPT-small model was used and finetuned on English to Spanish translations, extracted from http://storage.googleapis.com/download.tensorflow.org/data/spa-eng.zip

some examples of translations

Role	Response
User	please, sing me a song
Bot	Por favor, canta una canción.
User	I really want to go to China
Bot	Realmente quiero ir a China.
User	Can you do me a favor?
Bot	¿Me puedes hacer un favor?
User	I don't know what you are talking about
Bot	No sé de qué estás hablando.
User	I don't want to go to China
Bot	No quiero ir a China.

Using the model

example code for trying out the model

from transformers import AutoModelWithLMHead, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('microsoft/DialoGPT-small')
model = AutoModelWithLMHead.from_pretrained('OscarNav/dialoGPT_translate')

# Let's traslate 5 sentences
for step in range(5):
    # encode the new user input, add the eos_token and return a tensor in Pytorch
    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')

    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(
        new_user_input_ids, max_length=1000,
        pad_token_id=tokenizer.eos_token_id,
        top_p=0.92, top_k = 50
    )
    
    # pretty print last ouput tokens from bot
    print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, new_user_input_ids.shape[-1]:][0], skip_special_tokens=True)))

Downloads last month: 3