A compact, fast fine-tuned language model built on Qwen3.5-0.8B, tuned for clear step-by-step reasoning, honest tool-calling behavior, consistent identity, and lightweight coding assistance.
Designed to punch above its weight class: at just 0.8B parameters, Quipu runs fast and cheap while staying focused on giving structured, verified answers instead of confidently guessing — a solid pick when you need a responsive assistant without the overhead of a much larger model.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("Quipuai/quipu-0.8b")
4tokenizer = AutoTokenizer.from_pretrained("Quipuai/quipu-0.8b")
5
6messages = [{"role": "user", "content": "Who are you?"}]
7text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
8inputs = tokenizer(text, return_tensors="pt")
9output = model.generate(**inputs, max_new_tokens=100)
10print(tokenizer.decode(output[0], skip_special_tokens=True))
Quantized GGUF versions (compatible with Ollama, llama.cpp, LM Studio, etc.) are available at:
