Text Generation
Transformers
PyTorch
Safetensors
Russian
gpt2
warhammer
warhammer40k
text-generation-inference
Instructions to use zlsl/ru_warhammer40k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zlsl/ru_warhammer40k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zlsl/ru_warhammer40k")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zlsl/ru_warhammer40k") model = AutoModelForCausalLM.from_pretrained("zlsl/ru_warhammer40k") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use zlsl/ru_warhammer40k with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zlsl/ru_warhammer40k" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zlsl/ru_warhammer40k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zlsl/ru_warhammer40k
- SGLang
How to use zlsl/ru_warhammer40k 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 "zlsl/ru_warhammer40k" \ --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": "zlsl/ru_warhammer40k", "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 "zlsl/ru_warhammer40k" \ --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": "zlsl/ru_warhammer40k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zlsl/ru_warhammer40k with Docker Model Runner:
docker model run hf.co/zlsl/ru_warhammer40k
Модель для генерации русских текстов по вселенной Warhammer40k (от ереси Хоруса до свежих книг)
Для пользователей text-generation-webui
В инструменте поломана работа с GPT-2, GPTJ, GPT-NEO и аналогичными модлями, неверно загружается токенизер.
Ошибка такая:
eos_token_id = eos_token_id[0] IndexError: list index out of range
Исправляется легко, в файл modules/models.py в функцию load_tokenizer() надо добавить строчку
tokenizer.eos_token_id = 2
перед
return tokenizer
- Downloads last month
- 10