Sirius 10B

🚀 Sirius-10B

Sirius-10B is a merged model that combines the strengths of multiple pre - trained models. It offers enhanced performance by integrating the features of leveldevai/TurdusBeagle-7B and FelixChao/Severus-7B.

📄 License

This project is licensed under the Apache-2.0 license.

🧩 Configuration

The following is the configuration for merging the models:

slices:
  - sources:
    - model: leveldevai/TurdusBeagle-7B
      layer_range: [0, 24]
  - sources:
    - model: FelixChao/Severus-7B
      layer_range: [8, 32]
merge_method: passthrough
dtype: float16

💻 Usage Examples

Basic Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "FelixChao/Sirius-10B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])