|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
|
tags: |
|
|
- lora |
|
|
- qlora |
|
|
- script-writing |
|
|
- ads |
|
|
- youtube-shorts |
|
|
- reels |
|
|
- marketing |
|
|
- content-creation |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# SireIQ-Scripts 🧠✍️ |
|
|
|
|
|
**SireIQ-Scripts** is an instruction-tuned AI model for generating **viral content scripts**, including: |
|
|
- Short-form video scripts (Reels, TikTok, Shorts) |
|
|
- Marketing & ad copy |
|
|
- Image/video storytelling scripts |
|
|
- Hook-based social media content |
|
|
|
|
|
This model is **fine-tuned using LoRA** on top of **Mistral-7B-Instruct**. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🔧 Model Details |
|
|
|
|
|
- **Base Model:** mistralai/Mistral-7B-Instruct-v0.2 |
|
|
- **Fine-tuning:** LoRA / QLoRA |
|
|
- **Training Type:** Instruction-following |
|
|
- **Framework:** Hugging Face Transformers |
|
|
- **Environment:** Single GPU (Colab / Ubuntu) |
|
|
|
|
|
--- |
|
|
|
|
|
## 📥 How to Use |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
from peft import PeftModel |
|
|
|
|
|
base_model = "mistralai/Mistral-7B-Instruct-v0.2" |
|
|
lora_model = "your-username/SireIQ-Scripts" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(base_model) |
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
|
base_model, |
|
|
device_map="auto", |
|
|
load_in_4bit=True |
|
|
) |
|
|
|
|
|
model = PeftModel.from_pretrained(model, lora_model) |
|
|
|
|
|
prompt = """Write a viral Instagram reel script about AI replacing jobs.""" |
|
|
|
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device) |
|
|
outputs = model.generate(**inputs, max_new_tokens=200) |
|
|
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
|
|
