Instructions to use aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B with Transformers:

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

pipe = pipeline("text-generation", model="aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B")
model = AutoModelForCausalLM.from_pretrained("aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B

SGLang

How to use aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B 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 "aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B" \
    --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": "aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B",
		"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 "aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B" \
        --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": "aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B with Docker Model Runner:
```
docker model run hf.co/aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B
```

Aeoinum v1 BaseWeb 1B

A state-of-the-art language model for Russian language processing. This checkpoint contains a preliminary version of the model with 1.6 billion parameters. Trained only on web pages.

Models

Name	N of parameters	N of dataset tokens	Context window
Aeonium-v1-BaseWeb-1B	1.6B	32B	4K
Aeonium-v1-Base-1B	1.6B	In training	4K
Aeonium-v1-Chat-1B	1.6B	In training	4K

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B")
model = AutoModelForCausalLM.from_pretrained("aeonium/Aeonium-v1-Base-1.6B-checkpoint-20B").cuda()

input_ids = tokenizer("Искусственный интеллект - это", return_tensors='pt').to(model.device)["input_ids"]
output = model.generate(input_ids, max_new_tokens=48, do_sample=True, temperature=0.7)
print(tokenizer.decode(output[0]))

Output:

Искусственный интеллект - это основа современной науки и техники. Его потенциал позволяет решать задачи, которые выходят за пределы человеческих возможностей. В работе над ними участвуют все: от ученых до инженеров и даже военных. В своей книге "Искусственный интеллект" автор книги, профессор Л

Dataset Detail

The dataset for pre-training is collected from public data, most of which are web pages in Russian. The total size of the data is 20B tokens.

Training Detail

The training is performed thanks to a grant from TPU Research Cloud on a TPU v4-32 node.

Copyright

The model is released under the Apache 2.0 license.

Downloads last month: 8

Safetensors

Model size

2B params

Tensor type

F32