You can deploy this model and start earning money today!

IllegalXD12/
Zenithra

Name: Zenithra
Availability: InStock

mistralai/Mistral-7B-Instruct-v0.3

adapter

apache-2.0

Views

No views yet

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

python

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