Instructions to use jinymusim/gpt-czech-poet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jinymusim/gpt-czech-poet with Transformers:

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

pipe = pipeline("text-generation", model="jinymusim/gpt-czech-poet")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jinymusim/gpt-czech-poet")
model = AutoModelForCausalLM.from_pretrained("jinymusim/gpt-czech-poet", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jinymusim/gpt-czech-poet with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jinymusim/gpt-czech-poet

SGLang

How to use jinymusim/gpt-czech-poet 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 "jinymusim/gpt-czech-poet" \
    --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": "jinymusim/gpt-czech-poet",
		"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 "jinymusim/gpt-czech-poet" \
        --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": "jinymusim/gpt-czech-poet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jinymusim/gpt-czech-poet with Docker Model Runner:
```
docker model run hf.co/jinymusim/gpt-czech-poet
```

Czech Poetry GPT

GPT2 finetuned on Czech poetry from github project by
Institute of Czech Literature, Czech Academy of Sciences.

https://github.com/versotym/corpusCzechVerse

Done using GPT-Czech-Poet

https://github.com/jinymusim/GPT-Czech-Poet

https://arxiv.org/abs/2407.12790

Usage

Use as any other GPT2 style model

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("jinymusim/gpt-czech-poet")
model = AutoModelForCausalLM.from_pretrained("jinymusim/gpt-czech-poet")

# Input Poet Start
poet_start = "# AABB # 1900\nD"
poet_start = poet_start.strip()
tokenized_poet_start = tokenizer.encode(poet_start, return_tensors='pt')

# generated a continuation to it
out = model.generate(tokenized_poet_start, 
                                max_length=256,
                                do_sample=True,
                                top_k=50
                                early_stopping=True,
                                pad_token_id= tokenizer.pad_token_id,
                                eos_token_id = tokenizer.eos_token_id)

# Decode Poet
decoded_cont = tokenizer.decode(out[0], skip_special_tokens=True)

print(decoded_cont)

Downloads last month: 120

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for jinymusim/gpt-czech-poet

Base model

lchaloupsky/czech-gpt2-oscar

Finetuned

(1)

this model

Paper for jinymusim/gpt-czech-poet

GPT Czech Poet: Generation of Czech Poetic Strophes with Language Models

Paper • 2407.12790 • Published Jun 18, 2024