Instructions to use naltukhov/joke-generator-rus-t5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naltukhov/joke-generator-rus-t5 with Transformers:

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

pipe = pipeline("text-generation", model="naltukhov/joke-generator-rus-t5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("naltukhov/joke-generator-rus-t5")
model = AutoModelForSeq2SeqLM.from_pretrained("naltukhov/joke-generator-rus-t5")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use naltukhov/joke-generator-rus-t5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "naltukhov/joke-generator-rus-t5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "naltukhov/joke-generator-rus-t5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/naltukhov/joke-generator-rus-t5

SGLang

How to use naltukhov/joke-generator-rus-t5 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 "naltukhov/joke-generator-rus-t5" \
    --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": "naltukhov/joke-generator-rus-t5",
		"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 "naltukhov/joke-generator-rus-t5" \
        --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": "naltukhov/joke-generator-rus-t5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use naltukhov/joke-generator-rus-t5 with Docker Model Runner:
```
docker model run hf.co/naltukhov/joke-generator-rus-t5
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Task

Model create for jokes generation task on Russian language. Generate jokes from scratch is too difficult task. Too make it easier jokes was splitted into setup and punch pairs. Each setup can produce infinite number of punches so inspiration was also introduced, which means main idea (or main word) of punch for given setup. In the real world, jokes come in different qualities (bad, good, funny, ...). Therefore, in order for the models to distinguish them from each other, a mark was introduced. It ranges from 0 (not a joke) to 5 (golden joke).

Info

Model trained using flax on huge dataset with jokes and anekdots on different tasks:

Span masks (dataset size: 850K)
Conditional generation tasks (simultaneously):
a. Generate inspiration by given setup (dataset size: 230K)
b. Generate punch by given setup and inspiration (dataset size: 240K)
c. Generate mark by given setup and punch (dataset size: 200K)

Ethical considerations and risks

Model is fine-tuned on a large corpus of humorous text data scraped from from websites/telegram channels with anecdotes, shortliners, jokes. Text was not filtered for explicit content or assessed for existing biases. As a result the model itself is potentially vulnerable to generating equivalently inappropriate content or replicating inherent biases in the underlying data. Please don't take it seriously.

Downloads last month: 14