Downloads · 30 days
6
26% of all-time downloads
Zenithra
IllegalXD12/Zenithra
Zenithra is a machine learning model from IllegalXD12. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Your personal AI assistant, built for your projects.
All-time downloads
23
Public
Repo size
27.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.3 MB · 91%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026
- SHA
- d129e7a7
Base models
Model card
From the Hugging Face model README
Zenithra 🤖
Your personal AI assistant, built for your projects.
Zenithra is a fine-tuned version of Mistral-7B-Instruct-v0.3 using LoRA, trained to assist with personal projects, brainstorming, planning, and execution.
Model Details
| Property | Value |
|---|---|
| Base Model | mistralai/Mistral-7B-Instruct-v0.3 |
| Fine-tuning Method | LoRA (r=16, alpha=32) |
| Training Data | openassistant-guanaco |
| Quantization | 4-bit NF4 |
| Hardware | Google Colab T4 GPU |
How To Use
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base_model = "mistralai/Mistral-7B-Instruct-v0.3"
adapter = "IllegalXD12/Zenithra"
tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
prompt = "<s>[INST] You are Zenithra, a personal AI assistant. Help me plan my project. [/INST]"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
GitHub
Full code, inference script, and documentation: 👉 github.com/ItzVihang/Zenithra
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026