66 lines
2.0 KiB
Markdown
66 lines
2.0 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
base_model: Qwen/Qwen3-0.6B
|
|
language:
|
|
- en
|
|
tags:
|
|
- lora
|
|
- fine-tuned
|
|
- reasoning
|
|
- lightweight
|
|
- multilingual
|
|
- text-generation
|
|
- conversational
|
|
- instruction-tuned
|
|
- qwen3
|
|
- small-language-model
|
|
- efficient
|
|
---
|
|
|
|
# Quipu 0.6B
|
|
|
|
A compact, fast fine-tuned language model built on Qwen3-0.6B, tuned for clear step-by-step reasoning, consistent identity, and lightweight coding assistance.
|
|
|
|
Designed to punch above its weight class: at just 0.6B parameters, Quipu runs fast and cheap while staying focused on giving structured, logical answers — a solid pick when you need a responsive assistant without the overhead of a much larger model.
|
|
|
|
## Good for
|
|
|
|
- Step-by-step reasoning and simple logic problems
|
|
- Basic coding help (short functions, quick snippets)
|
|
- Fast, low-resource deployment (edge devices, quick prototyping, local inference)
|
|
|
|
## Model Details
|
|
|
|
- **Base model:** Qwen/Qwen3-0.6B
|
|
- **Fine-tuning method:** LoRA
|
|
- **Languages:** English, Spanish
|
|
- **License:** Apache 2.0
|
|
|
|
## How to Get Started
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("Quipuai/quipu-0.6b")
|
|
tokenizer = AutoTokenizer.from_pretrained("Quipuai/quipu-0.6b")
|
|
|
|
messages = [{"role": "user", "content": "Who are you?"}]
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
inputs = tokenizer(text, return_tensors="pt")
|
|
output = model.generate(**inputs, max_new_tokens=100)
|
|
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
|
```
|
|
|
|
## GGUF / Ollama
|
|
|
|
Quantized GGUF versions (compatible with Ollama, llama.cpp, LM Studio, etc.) are available thanks to [mradermacher](https://huggingface.co/mradermacher):
|
|
|
|
- [mradermacher/quipu-0.6b-GGUF](https://huggingface.co/mradermacher/quipu-0.6b-GGUF) — standard quants
|
|
- [mradermacher/quipu-0.6b-i1-GGUF](https://huggingface.co/mradermacher/quipu-0.6b-i1-GGUF) — imatrix quants (better quality)
|
|
|
|
To run with Ollama:
|
|
|
|
```bash
|
|
ollama run hf.co/mradermacher/quipu-0.6b-GGUF:Q4_K_M
|
|
``` |