初始化项目,由ModelHub XC社区提供模型
Model: Gaivoronsky/ruGPT-3.5-13B-fp16 Source: Original Platform
This commit is contained in:
35
README.md
Normal file
35
README.md
Normal file
@@ -0,0 +1,35 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- ru
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
tags:
|
||||
- gpt3
|
||||
- transformers
|
||||
- pytorch
|
||||
---
|
||||
This is a generative model converted to fp16 format based on [ai-forever/ruGPT-3.5-13B](https://huggingface.co/ai-forever/ruGPT-3.5-13B)
|
||||
|
||||
## Examples of usage
|
||||
|
||||
```python
|
||||
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))
|
||||
```
|
||||
Reference in New Issue
Block a user