Instructions to use KovrizhnykhDmitrii/Gptsmall with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KovrizhnykhDmitrii/Gptsmall with Transformers:

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

pipe = pipeline("text-generation", model="KovrizhnykhDmitrii/Gptsmall")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KovrizhnykhDmitrii/Gptsmall")
model = AutoModelForCausalLM.from_pretrained("KovrizhnykhDmitrii/Gptsmall")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KovrizhnykhDmitrii/Gptsmall with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/KovrizhnykhDmitrii/Gptsmall

SGLang

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

Docker Model Runner
How to use KovrizhnykhDmitrii/Gptsmall with Docker Model Runner:
```
docker model run hf.co/KovrizhnykhDmitrii/Gptsmall
```

rugpt3large_based_on_gpt2

Model was trained with sequence length 1024 using transformers lib by SberDevices team on 80B tokens for 3 epochs. After that model was finetuned 1 epoch with sequence length 2048.

Total training time was around 14 days on 128 GPUs for 1024 context and few days on 16 GPUs for 2048 context.
Final perplexity on test set is 13.6.

Downloads last month: 3