Instructions to use vietrix/viena-tiny-demo-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vietrix/viena-tiny-demo-pretrain with Transformers:

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

pipe = pipeline("text-generation", model="vietrix/viena-tiny-demo-pretrain")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vietrix/viena-tiny-demo-pretrain")
model = AutoModelForCausalLM.from_pretrained("vietrix/viena-tiny-demo-pretrain")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use vietrix/viena-tiny-demo-pretrain with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vietrix/viena-tiny-demo-pretrain

SGLang

How to use vietrix/viena-tiny-demo-pretrain 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 "vietrix/viena-tiny-demo-pretrain" \
    --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": "vietrix/viena-tiny-demo-pretrain",
		"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 "vietrix/viena-tiny-demo-pretrain" \
        --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": "vietrix/viena-tiny-demo-pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vietrix/viena-tiny-demo-pretrain with Docker Model Runner:
```
docker model run hf.co/vietrix/viena-tiny-demo-pretrain
```

Viena Tiny Pretrain (Base)

This is a tiny, pretrain-only Viena checkpoint. It is not instruction tuned. Use it as a base for further pretraining or SFT. It is intended for smoke tests only.

Model description

Architecture: decoder-only Transformer (VienaModel) with RMSNorm, RoPE, SwiGLU, GQA.
Parameters: ~10M (tiny config).
Tokenizer: SentencePiece BPE (target vocab 2000; actual vocab may be smaller due to tiny data).
Training: small offline synthetic dataset shipped with the repo.

Training data

Pretrain: viena_data/examples/pretrain_offline.jsonl

All datasets are synthetic and intended for offline tests.

Training recipe (tiny)

Config: configs/viena_tiny.yaml
Pretrain: 50 steps

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "vietrix/viena-tiny-demo-pretrain"
tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
)

prompt = "Viena la gi?
"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.9)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Limitations

Very small dataset and very few steps.
Not instruction tuned; responses are raw continuations.
Not suitable for real use or evaluation.

License

MIT (code + demo weights). See repository license for details.

Downloads last month: 2

Safetensors

Model size

847k params

Tensor type

F32