Pretrained Models
Collection
Pre-trained models have been trained on Vietnamese or multilingual data including Vietnamese. • 7 items • Updated
Hoa 7B (Bloom architecture)
Hoa is an autoregressive Large Language Model (LLM), based on Bloom's model architecture. Hoa was trained on part of the Common Crawl dataset in Vietnamese and English.
Details will be available soon.
To contact us, mail to: leanhcuong@gmail.com (Lê Anh Cường) | hieunguyen1053@outlook.com (Hiếu) | nv.cuong@int2.vn (Nguyễn Việt Cường)
How to use
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("vlsp-2023-vllm/hoa-7b")
model = AutoModelForCausalLM.from_pretrained("vlsp-2023-vllm/hoa-7b", low_cpu_mem_usage=True)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
prompt = "Địa chỉ trường Đại học Tôn Đức Thắng nằm ở số"
input_ids = tokenizer(prompt, return_tensors="pt")['input_ids'].to(device)
gen_tokens = model.generate(input_ids, max_length=max_length, repetition_penalty=1.1)
print(tokenizer.batch_decode(gen_tokens)[0])
- Downloads last month
- 22
Model tree for vlsp-2023-vllm/hoa-7b
Dataset used to train vlsp-2023-vllm/hoa-7b
Collection including vlsp-2023-vllm/hoa-7b
Evaluation results
- Perplexity on vi_lambadatest set self-reported8.111
- SacreBLEU on English to Vietnamese Formal/Informal translationtest set self-reported25.900