Luminia-13B-v3 / README.md
Nekochu's picture
Update README.md
602563f verified
metadata
model_creator: Nekochu
quantized_by: Nekochu
model_name: Luminia 13B v3
pretty_name: Luminia
model_type: llama2
prompt_template: >-
  Below is an instruction that describes a task. Write a response that
  appropriately completes the request. ### Instruction: {Instruction} {summary}
  ### input: {category} ### Response: {prompt}
base_model: meta-llama/Llama-2-13b-chat-hf
library_name: peft
license: apache-2.0
datasets:
  - Nekochu/discord-unstable-diffusion-SD-prompts
  - glaiveai/glaive-function-calling-v2
  - TIGER-Lab/MathInstruct
  - Open-Orca/SlimOrca
  - GAIR/lima
  - sahil2801/CodeAlpaca-20k
  - garage-bAInd/Open-Platypus
language:
  - en
pipeline_tag: text-generation
task_categories:
  - question-answering
  - text2text-generation
  - conversational
inference: true
widget:
  - example_title: prompt assistant
    messages:
      - role: system
        content: >-
          Below is an instruction that describes a task, paired with an input
          that provides further context. Write a response that appropriately
          completes the request.
      - role: user
        content: >
          ### Instruction:

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

          ### Input:

          favorites and popular SFW

          ### Response:
    output:
      text: Luminia, 1girl, solo, blonde hair, long hair,
tags:
  - llama-factory
  - lora
  - generated_from_trainer
  - llama2
  - llama
  - instruct
  - finetune
  - gpt4
  - synthetic data
  - stable diffusion
  - alpaca
  - llm
model-index:
  - name: Luminia-13B-v3
    results: []
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

Luminia v3 is good at reasoning to enhance Stable Diffusion prompt from short summary description, may output NSFW content.

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

Prompt template: Alpaca

Output example tested In text-generation-webui
Input base llama-2-chat QLoRa
[question]:

Create stable diffusion metadata based on the given english description. Luminia \n### Input:\n favorites and popular SFW
Answer:

Luminia, a mystical world of wonder and magic 🧝‍♀️✨ A place where technology and nature seamlessly blend together ...
Answer!

< 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 ....

Output prompt from QLoRa to A1111/SD-WebUI:

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: epicrealism_naturalSinRC1VAE, Version: v1.7.0
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: epicrealism_naturalSinRC1VAE, Version: v1.7.0

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.

Training Details

Click to see details

Model Description

  • Train by: Nekochu, Model type: Llama, Finetuned from model Llama-2-13b-chat

  • 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
  • num_train_epochs: 3.0
  • max_samples: 100000
  • warmup_steps: 0
  • train_batch_size: 1
  • distributed_type: single-GPU
  • num_devices: 1
  • warmup_steps: 0
  • rope_scaling: linear
  • lora_rank: 32
  • lora_target: all
  • lora_dropout: 0.15
  • bnb_4bit_compute_dtype: bfloat16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine

training_loss:

Nekochu

Framework versions

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