| --- |
| base_model: |
| - Sagicc/Occam-2B-CCoT |
| - allenai/tmax-2b |
| tags: |
| - merge |
| - mergekit |
| - lazymergekit |
| - Sagicc/Occam-2B-CCoT |
| - allenai/tmax-2b |
| --- |
| |
| # Papercut-2B |
|
|
| Papercut-2B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
| * [Sagicc/Occam-2B-CCoT](https://huggingface.co/Sagicc/Occam-2B-CCoT) |
| * [allenai/tmax-2b](https://huggingface.co/allenai/tmax-2b) |
|
|
| ## 🧩 Configuration |
|
|
| ```yaml |
| 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"]) |
| ``` |
