Instructions to use ClassCat/gpt2-small-catalan-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClassCat/gpt2-small-catalan-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ClassCat/gpt2-small-catalan-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ClassCat/gpt2-small-catalan-v2")
model = AutoModelForCausalLM.from_pretrained("ClassCat/gpt2-small-catalan-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ClassCat/gpt2-small-catalan-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClassCat/gpt2-small-catalan-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClassCat/gpt2-small-catalan-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ClassCat/gpt2-small-catalan-v2

SGLang

How to use ClassCat/gpt2-small-catalan-v2 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 "ClassCat/gpt2-small-catalan-v2" \
    --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": "ClassCat/gpt2-small-catalan-v2",
		"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 "ClassCat/gpt2-small-catalan-v2" \
        --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": "ClassCat/gpt2-small-catalan-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ClassCat/gpt2-small-catalan-v2 with Docker Model Runner:
```
docker model run hf.co/ClassCat/gpt2-small-catalan-v2
```

GPT2 Catalan small model Version 2 (Uncased)

Prerequisites

transformers==4.19.2

Model architecture

This model uses GPT2 base model settings, but the size of embedding dimensions are half the size of them.

Tokenizer

Using BPE tokenizer with vocabulary size 50,000.

Training Data

wiki40b/ca (Catalan Wikipedia)
Subset of oscar
Subset of CC-100/ca : Monolingual Datasets from Web Crawl Data

Usage

from transformers import pipeline

unmasker = pipeline('fill-mask', model='ClassCat/gpt2-small-catalan-v2')
unmasker("Ell està una mica")

Downloads last month: 5

ClassCat
/

gpt2-small-catalan-v2