Instructions to use Roaoch/CyberClassic-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Roaoch/CyberClassic-Generator with Transformers:

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

pipe = pipeline("text-generation", model="Roaoch/CyberClassic-Generator")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Roaoch/CyberClassic-Generator")
model = AutoModelForCausalLM.from_pretrained("Roaoch/CyberClassic-Generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Roaoch/CyberClassic-Generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Roaoch/CyberClassic-Generator

SGLang

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

Docker Model Runner
How to use Roaoch/CyberClassic-Generator with Docker Model Runner:
```
docker model run hf.co/Roaoch/CyberClassic-Generator
```

CyberClassic-Generator / README.md

Roaoch

Update README.md

a6cdb54 verified over 2 years ago

preview code

Raw History Blame Contribute Delete

1.33 kB

metadata

license: mit
language:
  - ru
metrics:
  - perplexity
  - bleu
  - rouge
library_name: transformers
pipeline_tag: text-generation

This text generator is based on OpenAI GPT2 model from HuggingFace Base model went through two step of learning

First - Finetining of base model

On this step model is finetuned on dataset of single sentence from the texts of Dostovesky F.M.

Training parameters:

Epoch = 10
Learning Rate = 1e-3
Optimizer = AdamW
Scheduler = OneCycleLR
Training env = PyTorch

Second - RL

On this step finetuned model went trough reinforcement learning pipline with TRL library.

Training parameters:

Epoch = 30
Trainer = PPO
Query texts = first 100 texts from dataset, trimmed by first 3 words
Reward = score from binary classifier multiplied by 10