Instructions to use MesonWarrior/gpt2-vk-bugro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MesonWarrior/gpt2-vk-bugro with Transformers:

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

pipe = pipeline("text-generation", model="MesonWarrior/gpt2-vk-bugro")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MesonWarrior/gpt2-vk-bugro")
model = AutoModelForCausalLM.from_pretrained("MesonWarrior/gpt2-vk-bugro", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MesonWarrior/gpt2-vk-bugro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MesonWarrior/gpt2-vk-bugro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MesonWarrior/gpt2-vk-bugro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MesonWarrior/gpt2-vk-bugro

SGLang

How to use MesonWarrior/gpt2-vk-bugro 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 "MesonWarrior/gpt2-vk-bugro" \
    --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": "MesonWarrior/gpt2-vk-bugro",
		"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 "MesonWarrior/gpt2-vk-bugro" \
        --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": "MesonWarrior/gpt2-vk-bugro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MesonWarrior/gpt2-vk-bugro with Docker Model Runner:
```
docker model run hf.co/MesonWarrior/gpt2-vk-bugro
```

MesonWarrior commited on Apr 7, 2023

Commit

cdfc29a

1 Parent(s): 4a0d700

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -3,6 +3,8 @@ language:
 - ru
 tags:
 - text-generation-inference
 ---
 # GPT-2 VK Bugro
 Зафайнтюненная на датасете VK паблика - "бугро тред" версия [ai-forever/rugpt3medium_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3medium_based_on_gpt2)

 - ru
 tags:
 - text-generation-inference
+- gpt2
+- PyTorch
 ---
 # GPT-2 VK Bugro
 Зафайнтюненная на датасете VK паблика - "бугро тред" версия [ai-forever/rugpt3medium_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3medium_based_on_gpt2)