Instructions to use tartuNLP/gpt-for-est-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tartuNLP/gpt-for-est-large with Transformers:

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

pipe = pipeline("text-generation", model="tartuNLP/gpt-for-est-large")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tartuNLP/gpt-for-est-large")
model = AutoModelForCausalLM.from_pretrained("tartuNLP/gpt-for-est-large")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tartuNLP/gpt-for-est-large with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tartuNLP/gpt-for-est-large

SGLang

How to use tartuNLP/gpt-for-est-large 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 "tartuNLP/gpt-for-est-large" \
    --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": "tartuNLP/gpt-for-est-large",
		"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 "tartuNLP/gpt-for-est-large" \
        --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": "tartuNLP/gpt-for-est-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tartuNLP/gpt-for-est-large with Docker Model Runner:
```
docker model run hf.co/tartuNLP/gpt-for-est-large
```

gpt-est-large

This is the large-size GPT2 model, trained from scratch on 2.2 billion words (Estonian National Corpus + News Crawl + Common Crawl). Previously named "gpt-4-est-large", renamed to avoid click-baiting.

Reference

Format

For training data was prepended with a text domain tag, and it should be added as prefix when using the model: >general<, >web<, >news<, >doaj< and >wiki< (standing for general texts, web crawled texts, news, article abstracts and wikipedia texts). Use the prefixes like this, e.g: ">web< Kas tead, et".

Model details

num. of layers: 24
num. of heads: 24
embedding size: 1536
context size: 1024
total size: 723.58M params

Further details to be added soon.

Framework versions

Transformers 4.13.0.dev0
Pytorch 1.10.0+cu102
Datasets 1.15.1
Tokenizers 0.10.3

Downloads last month: 11

Safetensors

Model size

0.8B params

Tensor type

F32