slices:
  - sources:
    - model: ryan0712/llama-3-8b-DUS-initialized
      layer_range: [0, 21]
  - sources:
    - model: ryan0712/llama-3-8b-slow-DUS-layer-SLERP
      layer_range: [0, 1]
  - sources:
    - model: ryan0712/llama-3-8b-DUS-initialized
      layer_range: [21, 48]
merge_method: passthrough
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ryan0712/llama-3-8b-slow-DUS-method-1"
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"])