|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
- ru |
|
|
- uk |
|
|
base_model: |
|
|
- openai/gpt-oss-20b |
|
|
--- |
|
|
# 🔥 PyroNet |
|
|
|
|
|
**PyroNet** is a fine-tuned and customized open-source large language model with a unique system identity. |
|
|
Originally based on **[gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b)**, this model has been **further trained and specialized** to embody the **PyroNet persona**. |
|
|
Created and maintained by **IceL1ghtning** from **Ukraine** 🇺🇦. |
|
|
|
|
|
--- |
|
|
|
|
|
## ✨ Features |
|
|
- 🧠 Fine-tuned on custom datasets to define the **PyroNet identity** |
|
|
- 🎭 Optimized for **chat, reasoning, coding, and explanation tasks** |
|
|
- 🔗 Fully compatible with the Hugging Face `transformers` ecosystem |
|
|
- 📦 Includes a custom **chat template** and structured **system prompt** |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚀 Usage |
|
|
|
|
|
### Install requirements |
|
|
```bash |
|
|
pip install transformers accelerate bitsandbytes |
|
|
``` |
|
|
|
|
|
### Quick inference |
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline |
|
|
|
|
|
model_id = "Kenan023214/PyroNet" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") |
|
|
|
|
|
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer) |
|
|
|
|
|
prompt = "Hello, PyroNet! Can you introduce yourself?" |
|
|
result = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.8) |
|
|
|
|
|
print(result[0]["generated_text"]) |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
### 💡 Recommendations |
|
|
|
|
|
Best run on GPU with ≥24 GB VRAM (e.g. RTX 3090, A100). |
|
|
|
|
|
For smaller GPUs, use: |
|
|
|
|
|
```python |
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
|
model_id, |
|
|
device_map="auto", |
|
|
load_in_8bit=True |
|
|
) |
|
|
``` |
|
|
(Requires bitsandbytes). |
|
|
|
|
|
Adjust temperature and top_p for more creative or deterministic outputs. |
|
|
|
|
|
|
|
|
|
|
|
--- |
|
|
|
|
|
|
|
|
[💬 Telegram](https://t.me/LogovoOfEngineer) |
|
|
|
|
|
📧 Contact: engineerglab@gmail.com |
|
|
|
|
|
|
|
|
--- |
|
|
|
|
|
### 📜 License & Disclaimer |
|
|
|
|
|
License: Apache 2.0 |
|
|
|
|
|
Based on gpt-oss-20b |
|
|
|
|
|
For research purposes only. Not intended for production without further alignment and safety checks. |
|
|
|
|
|
Responsibility for usage lies with the end-user. |
|
|
|
|
|
|
|
|
|
|
|
--- |
|
|
|
|
|
🔥 PyroNet — Where logic meets creativity. |
