models:
  - model: Qwen/Qwen3.5-2B # Base
  - model: Sagicc/Occam-2B-CCoT # Short Thinking + Tool Calling
    parameters:
      weight: 1.0
      density: 0.9
      gamma: 0.01
  - model: allenai/tmax-2b # Terminal Agent
    parameters:
      weight: 1.0
      density: 0.9
      gamma: 0.01
merge_method: breadcrumbs_ties
base_model: Qwen/Qwen3.5-2B

💻 Usage

python

!uv pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "sillykiwi/Papercut-2B"
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"])