110 lines
4.0 KiB
Markdown
110 lines
4.0 KiB
Markdown
|
---
|
|||
|
|
library_name: transformers
|
|||
|
|
license: apache-2.0
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
tags:
|
|||
|
|
- qwen2.5
|
|||
|
|
- 0.5B
|
|||
|
|
- conversational
|
|||
|
|
- fast
|
|||
|
|
- lightweight
|
|||
|
|
- quantsaparklabs
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
|||
|
|
---
|
|||
|
|
<p align="center">
|
|||
|
|
<img src="https://huggingface.co/QuantaSparkLabs/NYXIS-Pro/resolve/main/preview imgagee.png"
|
|||
|
|
alt="NYXIS Logo"
|
|||
|
|
width="160"
|
|||
|
|
height="160"
|
|||
|
|
style="border-radius: 50%; object-fit: cover;">
|
|||
|
|
</p>
|
|||
|
|
|
|||
|
|
<p align="center">
|
|||
|
|
<img src="https://huggingface.co/QuantaSparkLabs/NYXIS-Pro/resolve/main/logoname.png"
|
|||
|
|
alt="NYXIS Name"
|
|||
|
|
width="700"
|
|||
|
|
style="border-radius: 18px;">
|
|||
|
|
</p>
|
|||
|
|
|
|||
|
|
<p align="center">
|
|||
|
|
<a href="https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct"><img src="https://img.shields.io/badge/Base-Qwen%202.5%200.5B-blueviolet" alt="Base Model"></a>
|
|||
|
|
<a href="https://huggingface.co/datasets/teknium/OpenHermes-2.5"><img src="https://img.shields.io/badge/Data-OpenHermes%202.5-00BFFF" alt="Training Data"></a>
|
|||
|
|
<a href="#"><img src="https://img.shields.io/badge/Fine--Tune-QLoRA%20%2B%20Unsloth-FF6F00" alt="Fine-Tune Method"></a>
|
|||
|
|
<a href="#"><img src="https://img.shields.io/badge/Size-0.5B%20Params-lightgrey" alt="Model Size"></a>
|
|||
|
|
<a href="#"><img src="https://img.shields.io/badge/Speed-Blazing%20Fast-brightgreen" alt="Speed"></a>
|
|||
|
|
<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-yellow" alt="License"></a>
|
|||
|
|
</p>
|
|||
|
|
|
|||
|
|
# Quantum-X
|
|||
|
|
|
|||
|
|
A compact, high‑speed conversational AI built on **Qwen 2.5 0.5B** — small enough for edge devices, smart enough for real conversation.
|
|||
|
|
|
|||
|
|
## 📋 Overview
|
|||
|
|
|
|||
|
|
Quantum‑X is a **0.5 billion parameter** language model developed by QuantaSparkLabs. It's fine‑tuned from Qwen 2.5 0.5B on a mix of OpenHermes‑2.5 conversations and custom identity data, giving it warm, direct conversational abilities while keeping inference blazingly fast.
|
|||
|
|
|
|||
|
|
| Feature | Detail |
|
|||
|
|
|---------|--------|
|
|||
|
|
| **Base Model** | Qwen 2.5 0.5B‑Instruct |
|
|||
|
|
| **Parameters** | ~0.5B |
|
|||
|
|
| **Fine‑tuning** | QLoRA (Unsloth), 2 epochs |
|
|||
|
|
| **Training Data** | OpenHermes‑2.5 + identity examples |
|
|||
|
|
| **Tensor Precision** | FP16 |
|
|||
|
|
| **Chat Template** | ✅ Native Qwen2 chat template |
|
|||
|
|
|
|||
|
|
## ✨ What It Does Well
|
|||
|
|
|
|||
|
|
- **Conversational AI**: Natural, warm dialogue with identity baked in.
|
|||
|
|
- **Factual Q&A**: Answers general knowledge questions correctly.
|
|||
|
|
- **Fast Inference**: 0.5B parameters = near‑instant responses on CPU or GPU.
|
|||
|
|
- **Edge Friendly**: Runs comfortably on 2 GB RAM, even on a phone.
|
|||
|
|
|
|||
|
|
## 💻 Quick Start
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|||
|
|
import torch
|
|||
|
|
|
|||
|
|
model_id = "QuantaSparkLabs/Quantum-X"
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
|||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|||
|
|
model_id,
|
|||
|
|
torch_dtype=torch.float16,
|
|||
|
|
device_map="auto",
|
|||
|
|
trust_remote_code=True
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
messages = [
|
|||
|
|
{"role": "system", "content": "You are Quantum-X, created by QuantaSparkLabs."},
|
|||
|
|
{"role": "user", "content": "What is the capital of France?"}
|
|||
|
|
]
|
|||
|
|
inputs = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|||
|
|
input_ids = tokenizer(inputs, return_tensors="pt").to(model.device)
|
|||
|
|
|
|||
|
|
outputs = model.generate(**input_ids, max_new_tokens=100, temperature=0.7, do_sample=True)
|
|||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 🚀 Hardware Requirements
|
|||
|
|
|
|||
|
|
| Environment | RAM | Storage | Ideal For |
|
|||
|
|
| :--- | :--- | :--- | :--- |
|
|||
|
|
| **CPU** | 2 GB | ~500 MB | Testing, embedded apps |
|
|||
|
|
| **GPU** | 1‑2 GB VRAM | ~500 MB | Development, serving |
|
|||
|
|
| **Edge / Mobile** | >1 GB | ~500 MB | On‑device inference |
|
|||
|
|
|
|||
|
|
## ⚠️ Limitations
|
|||
|
|
|
|||
|
|
- **Complex reasoning**: Multi‑step logic or advanced math may be inconsistent.
|
|||
|
|
- **Factual precision**: Can occasionally produce outdated or incorrect information.
|
|||
|
|
- **Not for high‑stakes use**: Don't use for medical, legal, or safety‑critical decisions.
|
|||
|
|
|
|||
|
|
## 📄 License
|
|||
|
|
|
|||
|
|
Apache 2.0
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
<center>Built with ❤️ by QuantaSparkLabs<br>Model ID: Quantum‑X • Rebuilt 2026</center>
|