Downloads · 30 days
112
5% of all-time downloads
Gaivoronsky/ruGPT-3.5-13B-fp16
ruGPT-3.5-13B-fp16 is a text generation model from Gaivoronsky. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
This is a generative model converted to fp16 format based on ai-forever/ruGPT-3.5-13B
Downloads · 30 days
112
5% of all-time downloads
All-time downloads
2.5K
Public
Repo size
51.4 GB
Likes
12
Public
Click a slice to open those files.
.bin25.7 GB · 100%
From the Hugging Face model README
This is a generative model converted to fp16 format based on ai-forever/ruGPT-3.5-13B
from transformers import GPT2LMHeadModel, AutoTokenizer
model = GPT2LMHeadModel.from_pretrained('Gaivoronsky/ruGPT-3.5-13B-fp16')
tokenizer = AutoTokenizer.from_pretrained('Gaivoronsky/ruGPT-3.5-13B-fp16')
model = model.half()
model = model.to('cuda')
request = "Человек: Сколько весит жираф? Помощник: "
encoded_input = tokenizer(request, return_tensors='pt', \
add_special_tokens=False).to('cuda')
output = model.generate(
**encoded_input,
num_beams=2,
do_sample=True,
max_new_tokens=100
)
print(tokenizer.decode(output[0], skip_special_tokens=True))