|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- wikimedia/wikipedia |
|
|
- roneneldan/TinyStories |
|
|
- ajibawa-2023/Children-Stories-Collection |
|
|
- stas/c4-en-10k |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# Serayuki-1B |
|
|
|
|
|
**Model Developer**: Vynie |
|
|
<br> |
|
|
**Model Type**: Causal Language Model |
|
|
|
|
|
## Example Usage |
|
|
|
|
|
Using Hugging Face Transformers: |
|
|
|
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("SeraphyneLab/Serayuki-1B") |
|
|
tokenizer = AutoTokenizer.from_pretrained("SeraphyneLab/Serayuki-1B") |
|
|
|
|
|
input_text = "Once upon a time" |
|
|
inputs = tokenizer(input_text, return_tensors="pt").to("cuda") |
|
|
outputs = model.generate(**inputs, max_new_tokens=128) |
|
|
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
|
``` |
|
|
|
|
|
## License |
|
|
|
|
|
This model is licensed under the [MIT License](https://opensource.org/licenses/MIT). |
|
|
|
|
|
## Tokenizer Notice |
|
|
|
|
|
This model was trained from scratch; however, it uses the tokenizer from Meta’s LLaMA 3.2 3B Instruct model. As such, the tokenizer is subject to Meta’s [LLaMA 3 license](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt). Please review their terms before using this model or tokenizer in commercial applications. |
