needle3 / README.md
Amdkn7's picture henryNdubuaku's picture
Duplicate from Cactus-Compute/needle3
0c7b8f2
|
Raw History Blame Contribute Delete
1.53 kB
---
library_name: cactus-compute
pipeline_tag: text-generation
license: apache-2.0
tags:
- tool-calling
- function-calling
- on-device
- edge
- quantization
- webassembly
---
![Cactus Compute - Sub-50mb Super Intelligence For Consumer Devices](https://raw.githubusercontent.com/cactus-compute/cactus/main/assets/banner.svg)
# Needle 3
An on-device model for tool calling, structured extraction and text embeddings.
See the [Needle website](https://cactuscompute.com/needle) for model details, benchmarks and the browser demo.
## Get started
```sh
pip install -U cactus-compute
```
```python
import cactus
@cactus.tool
def get_weather(city: str):
"Get the current weather for a city."
return {"city": city, "temp_c": 27, "sky": "clear"}
with cactus.Cactus(tools=[get_weather]) as agent:
print(agent.run("What's the weather in Lagos?")["results"])
```
The package downloads and caches the engine and weights on first use.
This repository provides `needle3.cact` and `checkpoints/needle3.safetensors`.
[Runtime binaries and supported platforms](https://huggingface.co/Cactus-Compute/cactus) live in the Cactus repository.
## Guides
- [Python API](https://cactuscompute.com/blog/needle-python-docs)
- [Designing tools](https://cactuscompute.com/blog/designing-tools-for-needle) and [structured extraction](https://cactuscompute.com/blog/structured-extraction-with-needle)
- [Fine-tuning](https://cactuscompute.com/blog/finetuning-needle)
- [Source code](https://github.com/cactus-compute/cactus)