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

Libraries

How to use tosin/dialogpt_afriwoz_wolof with Transformers:

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

pipe = pipeline("text-generation", model="tosin/dialogpt_afriwoz_wolof")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tosin/dialogpt_afriwoz_wolof")
model = AutoModelForCausalLM.from_pretrained("tosin/dialogpt_afriwoz_wolof")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tosin/dialogpt_afriwoz_wolof with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tosin/dialogpt_afriwoz_wolof"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tosin/dialogpt_afriwoz_wolof",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tosin/dialogpt_afriwoz_wolof

SGLang

How to use tosin/dialogpt_afriwoz_wolof 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 "tosin/dialogpt_afriwoz_wolof" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tosin/dialogpt_afriwoz_wolof",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tosin/dialogpt_afriwoz_wolof" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tosin/dialogpt_afriwoz_wolof",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

YAML Metadata Error:"datasets[0]" with value "multi_woz_v22 and AfriWOZ" is not valid. If possible, use a dataset id from https://hf.co/datasets.

DialoGPT_AfriWOZ

This is a fine-tuned model of DialoGPT (small) on the AfriWOZ dataset. It is intended to be used as a conversational system in Wolof language. The dataset it's trained on is limited in scope, as it covers only certain domains such as restaurants, hotel, taxi, and booking.

The perplexity achieved on the test and validation sets are 20.74 and 11.66, respectively.

Generation example from an interactive environment:

Role	Response
User	sowwu bi la bëg
Bot	waw, ndax mën ngan ma jox ay leeral si bërëb buñu feetee ak lekkukaay bi
User	soxla na dem gawu. ngir leeral rek bëg na joggee peterborough di dem cambridge
Bot	soxlu na dem ginaw jurrom ñenti waxtu ak ñaar fukki simili ak jurrom ben.
User	waw jiss sal ma ben bu seer si njëg si toluway
Bot	jënd bi baaxna. jerejef. ba benen yoon.

Please find the information about preprocessing, training and full details of the DialoGPT in the original DialoGPT repository

The paper for this work can be found on arXiv: https://arxiv.org/pdf/2204.08083.pdf

How to use

Now we are ready to try out how the model works as a chatting partner!

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("tosin/dialogpt_afriwoz_wolof")
model = AutoModelForCausalLM.from_pretrained("tosin/dialogpt_afriwoz_wolof")
# Let's chat for 5 lines
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')
    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
    # pretty print last ouput tokens from bot
    print("DialoGPT_wolof_Bot: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))

Downloads last month: 4

Paper for tosin/dialogpt_afriwoz_wolof

AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages

Paper • 2204.08083 • Published Apr 17, 2022