qwen2
ExocoreV1 / README.md
Helenbaclayon Bacalso
Add Space demo link to README
d264ba1
|
Raw
History Blame Contribute Delete
757 Bytes
---
license: mit
---
# ExocoreV1
[![Open In Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/ChoruYt/ExocoreV1)
A 751M-parameter language model built from scratch by Exocore.
## Try it
**[Launch Chat Demo](https://huggingface.co/spaces/ChoruYt/ExocoreV1)** — Test the model directly in your browser.
## Features
- Multi-thinking modes (Fast, Thinking, Deep Think)
- Web search integration
- Custom training pipeline
- 40K context window
- RoPE, GQA, SwiGLU
## Usage
```python
from huggingface_hub import hf_hub_download
import torch
# Download model
path = hf_hub_download("Exocore/ExocoreV1", "Exocore.pt")
ckpt = torch.load(path, map_location="cpu")
print(f"Model loaded: {ckpt['config']}")
```