language:
- ru
license: apache-2.0
pipeline_tag: text-generation
tags:
- aeonium
inference:
parameters:
temperature: 0.8
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 |
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("aeonium/Aeonium-v1-BaseWeb-1B")
model = AutoModelForCausalLM.from_pretrained("aeonium/Aeonium-v1-BaseWeb-1B").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 не только про компьютеры и смартфоны. Его возможности безграничны, а с развитием интернета и интернета вещей он становится еще и самым настоящим оружием в борьбе с преступностью.
Мы поговорили с юристом о самых интересных и опасных способах использования ИИ.
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 32B tokens.
Training Detail
The training is performed thanks to a grant from TPU Research Cloud on a TPU v4-128 node.
Loss: 2.68; Accuracy: 0.48; Batch Size: 1024
Content Warning and Disclaimer
The Aeonium v1 language model can potentially generate text that contains biases, offensive language, misinformation, or other inappropriate content. As an AI system trained on broad data from the internet, it may reflect societal biases and produce content that is disapproving or objectionable. The creators cannot control or filter all possible outputs of the model.
The developers of Aeonium v1 condemn hate speech, discrimination, explicit violence, and other harmful content. However, they cannot guarantee the model will never generate such content. Users should exercise caution and critical judgment when using Aeonium v1.
The creators of Aeonium v1 shall not be held responsible for any improper, offensive, illegal or consequential damages arising from outputs generated by the model. Users access and utilize Aeonium v1 at their own risk.
Copyright
The model is released under the Apache 2.0 license.