Nekochu/Luminia-13B-v3

<div style="display: flex;"> <div style="flex: 1;"> <img src="https://i.imgur.com/uyjdkhk.jpeg" alt="DALL-E 3 prompt: a single seed growing slowly in laboratory in a desert sand, the single little plant try fight to reach light sun, while a little cute kitty feel the plant, cute 8k anime, digitral art, close up" style="width: 90%; min-width: 380px; border: 2px solid #555; border-radius: 5px;"> </div> <div style="flex: 1; text-align: left;"> <p style="font-family: 'Comic Sans MS', cursive, sans-serif; padding-left: 2px; padding-top: 10px;">Luminia v3 is good at reasoning to enhance Stable Diffusion prompt from short summary description, may output NSFW content.</p> </div> </div>

LoRa is include and Quants: exllamav2 2.4bpw-h6, 4.25bpw-h6, 8.0bpw-h8 | GGUF Q4_K_M, IQ4_NL |

Prompt template: Alpaca

<details> <summary>Output example tested In <i>text-generation-webui</i></summary>

Output prompt from QLoRa to A1111/SD-WebUI:

<div style="display: flex; justify-content: space-between;"> <div style="flex: 1; text-align: center;"> <img src="https://i.imgur.com/rNLaobj.png" alt="parameters image metadata: <lora:Luminari-10:0.8> Luminari, 1girl, solo, blonde hair, long hair, blue eyes, (black dress), looking at viewer, night sky, starry sky, constellation, smile, upper body, outdoors, forest, moon, tree, mountain, light particle, shine, sparkle, dark theme, fantasy, magic, goddess, celestial, nature, peaceful, serene, tranquil, mystical, enchanting, otherworldly, mysterious, captivating, alluring, beautiful, elegant, graceful, majestic, divine, powerful, epic, grand, sweeping, breathtaking, mesmerizing, magical, fantastical, wondrous, marvelous, extraordinary, magnificent, glorious, radiant, luminous, illumination, brilliance, glow, radiance, luminescence, brightness, splendor, glory, triumph, victory, achievement, honor, celebration, recognition, praise, admiration, appreciation, love, affection, devotion, loyalty, dedication, commitment, passion, intensity, drive, determination, energy, enthusiasm, excitement, joy, happiness, fulfillment, pleasure, enjoyment, satisfaction, delight, wonder, amazement, awe, curiosity, interest, intrigue, question, exploration, discovery, adventure, journey, path, road, trail, course, pursuit, challenge, obstacle, adversity, hardship, struggle, perseverance, resilience, tenacity, courage, bravery, heroism, inspiration, motivation, spirit, heart, soul, essence, creativity, imagination, dreams, aspirations, goals, ambition, vision, purpose, meaning, significance, relevance, importance, impact, influence, change, growth, development, evolution, improvement, progress, learning, knowledge, wisdom, insight, understanding, empathy, compassion, kindness, generosity, forgiveness, gratitude, humility, patience, tolerance, acceptance, diversity, inclusivity, unity, equality, justice, fairness, honesty, integrity, accountability, responsibility, morality, ethics, principles, values, beliefs, faith, hope, optimism, Steps: 20, Sampler: Heun, CFG scale: 7, Seed: 479539365, Size: 512x512, Model hash: 84d76a0328, Model: epicrealismnaturalSinRC1VAE, Version: v1.7.0" style="width: 100%; min-width: 200px; display: block; margin: auto;"> </div> <div style="flex: 1; text-align: center;"> <img src="https://i.imgur.com/hU8Ut4p.png" alt="parameters image metadata: <lora:Luminari-10:0.8> Luminari, 1girl, solo, blonde hair, long hair, blue eyes, (black dress), looking at viewer, night sky, starry sky, constellation, smile, upper body, outdoors, forest, moon, tree, mountain, light particle, shine, sparkle, dark theme, fantasy, magic, goddess, celestial, nature, peaceful, serene, tranquil, mystical, enchanting, otherworldly, mysterious, captivating, alluring, beautiful, elegant, graceful, majestic, divine, powerful, epic, grand, sweeping, breathtaking, mesmerizing, magical, fantastical, wondrous, marvelous, extraordinary, magnificent, glorious, radiant, luminous, illumination, brilliance, glow, radiance, luminescence, brightness, splendor, glory, triumph, victory, achievement, honor, celebration, recognition, praise, admiration, appreciation, love, affection, devotion, loyalty, dedication, commitment, passion, intensity, drive, determination, energy, enthusiasm, excitement, joy, happiness, fulfillment, pleasure, enjoyment, satisfaction, delight, wonder, amazement, awe, curiosity, interest, intrigue, question, exploration, discovery, adventure, journey, path, road, trail, course, pursuit, challenge, obstacle, adversity, hardship, struggle, perseverance, resilience, tenacity, courage, bravery, heroism, inspiration, motivation, spirit, heart, soul, essence, creativity, imagination, dreams, aspirations, goals, ambition, vision, purpose, meaning, significance, relevance, importance, impact, influence, change, growth, development, evolution, improvement, progress, learning, knowledge, wisdom, insight, understanding, empathy, compassion, kindness, generosity, forgiveness, gratitude, humility, patience, tolerance, acceptance, diversity, inclusivity, unity, equality, justice, fairness, honesty, integrity, accountability, responsibility, morality, ethics, principles, values, beliefs, faith, hope, optimism Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 959582434, Size: 512x512, Model hash: 84d76a0328, Model: epicrealismnaturalSinRC1VAE, Version: v1.7.0" style="width: 100%; min-width: 200px; display: block; margin: auto;"> </div> </div>

Full Prompt

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
Create stable diffusion metadata based on the given english description. Luminia

### Input:
favorites and popular SFW

### Response:

"Luminia" can be any short description, more info on my SD dataset here.

</details>

Training Details

<details> <summary>Click to see details</summary>

Model Description

• —Train by: Nekochu, Model type: Llama, Finetuned from model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)
• —Continue from the base of LoRA Luminia-13B-v2-QLora

Know issue: [issue]

Trainer

• —hiyouga/LLaMA-Efficient-Tuning

Hardware: QLoRA training OS Windows, Python 3.10.8, CUDA 12.1 on 24GB VRAM.

Training hyperparameters

The following hyperparameters were used during training:

• —num_epochs: 1.0
• —finetuning_type: lora
• —quantization_bit: 4
• —stage: sft
• —learning_rate: 5e-05
• —cutoff_len: 4096
• —numtrainepochs: 3.0
• —max_samples: 100000
• —warmup_steps: 0
• —trainbatchsize: 1
• —distributed_type: single-GPU
• —num_devices: 1
• —warmup_steps: 0
• —rope_scaling: linear
• —lora_rank: 32
• —lora_target: all
• —lora_dropout: 0.15
• —bnb4bitcompute_dtype: bfloat16
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine

training_loss:

<div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/qhuPG6F.jpg" alt="Nekochu" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div>

Framework versions

• —PEFT 0.9.0
• —Transformers 4.38.1
• —Pytorch 2.1.2+cu121
• —Datasets 2.14.5
• —Tokenizers 0.15.0

</details>