slices:
- sources:
  - layer_range: [0, 22]
    model: aipib/Dopey-karasu-MoE3
    parameters:
      density: [1, 0.7, 0.1]
      weight: 1.0
  - layer_range: [0, 22]
    model: AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
    parameters:
      density: 0.53
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: dare_ties
base_model: aipib/Dopey-karasu-MoE3
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "aipib/TinyMoE-DopeykarasuMoe-xdareties2"
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"])