L3.3-GeneticLemonade-Unleashed-v3-70B

<!DOCTYPE html> <style> /* Base styling for cyberpunk theme */ body {font-family: sans-serif; background-color: #080c14; color: #e1e9f0; line-height: 1.6; margin: 0; padding: 0;} .lemonade-text { color: #33ff99; position: relative; /* Keep relative positioning */ z-index: 2; margin-left: 0.2em; text-shadow: 0 0 10px #33ff99; /* Add static glow */ } /* Section styling */ .section-container {background-color: rgba(8, 12, 20, 0.7); margin-bottom: 30px; position: relative; overflow: hidden; border-bottom: 1px solid #33ff99;} .section-header {display: flex; align-items: center; background-color: rgba(0, 195, 255, 0.1); padding: 10px 20px;} .section-indicator {width: 8px; height: 20px; background-color: #33ff99; margin-right: 15px;} .section-title {font-family: 'Orbitron', sans-serif; color: #e1e9f0; font-size: 1.3rem; margin: 0; letter-spacing: 2px; text-transform: uppercase; font-weight: 500;} .section-content {padding: 20px; font-family: sans-serif; color: #e1e9f0; line-height: 1.6;} /* Title styling */ .title-container { background-color: #080c14; position: relative; overflow: hidden; margin-bottom: 40px; border-left: 3px solid #33ff99; } .title-wrapper { position: relative; z-index: 2; padding: 25px 20px 30px 30px; font-family: 'Orbitron', sans-serif; } .title-main { color: #e1e9f0; font-size: 2.5rem; /* Reduced font size */ font-weight: 700; margin: 0; letter-spacing: 2px; display: inline-block; position: relative; text-transform: uppercase; } .title-prefix { position: relative; z-index: 2; } .title-subtitle { padding-left: 15px; margin-top: 5px; margin-left: 5px; } .subtitle-text { color: #00c3ff; font-size: 1.2rem; /* Reduced font size */ font-family: 'Orbitron', sans-serif; font-weight: 300; letter-spacing: 3px; text-transform: uppercase; display: inline-block; } .glitchy-overlay { position: absolute; top: 0; left: 0; width: 100%; height: 100%; background-image: repeating-linear-gradient(0deg, rgba(0,0,0,0) 0, rgba(0,0,0,0.1) 1px, rgba(0,0,0,0) 2px); z-index: 1; } /* Data box styling */ .data-box {background-color: rgba(0, 0, 0, 0.2); padding: 15px; border-left: 2px solid #33ff99; margin-bottom: 20px;} .data-row {display: flex; margin-bottom: 8px;} .data-arrow {color: #33ff99; width: 20px; display: inline-block;} .data-label {color: #00c3ff; width: 80px; display: inline-block;} /* Subheading styling */ .subheading {color: #00c3ff; font-size: 1.1rem; margin-top: 20px; margin-bottom: 15px; font-weight: 400; border-bottom: 1px dashed rgba(0, 195, 255, 0.3); display: inline-block; text-transform: uppercase; letter-spacing: 1px; font-family: 'Orbitron', sans-serif;} /* Links */ a {color: #00c3ff; text-decoration: none;} a:hover {text-decoration: underline;} /* Container */ .container {max-width: 1200px; margin: 0 auto; padding: 40px 20px;} /* Cyberpunk grid background */ .cyber-grid-bg {position: fixed; top: 0; left: 0; right: 0; bottom: 0; background-color: #05071b; background-image: linear-gradient(rgba(0, 194, 255, 0.03) 1px, transparent 1px), linear-gradient(90deg, rgba(0, 194, 255, 0.03) 1px, transparent 1px); background-size: 20px 20px; z-index: -1;} </style> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>GENETIC LEMONADE UNLEASHED v3</title> <link href="https://fonts.googleapis.com/css2?family=Orbitron:wght@400;500;600;700&family=JetBrains+Mono:wght@100;300;400;700&display=swap" rel="stylesheet"> </head> <body> <div class="cyber-grid-bg"></div> <div class="container"> <div class="title-container"> <!-- Glitchy overlay --> <div class="glitchy-overlay"></div> <!-- Main title --> <div class="title-wrapper"> <h1 class="title-main"> <span class="title-prefix">GENETIC</span> <span class="lemonade-text">LEMONADE</span> <!-- Static text with glow --> </h1> <div class="title-subtitle"> <span class="subtitle-text">UNLEASHED v3</span> </div> </div> </div>

<div class="section-container"> <div class="section-header"> <div class="section-indicator"></div> <h2 class="section-title">01 // OVERVIEW</h2> </div> <div class="section-content"> <p>An experimental release.</p> <p><a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-70B">zerofata/GeneticLemonade-Unleashed</a> SFT+DPO QLora finetune.</p> <p>This is a creative model intended to excel at character driven RP / ERP. It has not been tested or trained on adventure stories or any large amounts of creative writing.</p> <p>This model is designed to provide longer, narrative heavy responses where characters are portrayed accurately and proactively.</p> </div> </div> <div class="section-container"> <div class="section-header"> <div class="section-indicator"></div> <h2 class="section-title">02 // SILLYTAVERN SETTINGS</h2> </div> <div class="section-content"> <p>Play with these, they are not the 'best' settings just a stable baseline. Something interesting to note is this model supports higher temps than would normally be recommended for other L3 models.</p> <h3 class="subheading">Recommended Samplers</h3> <div class="data-box"> <div class="data-row"> <span class="data-arrow">></span> <span class="data-label">Temp:</span> <span>0.9 - 1.2</span> </div> <div class="data-row"> <span class="data-arrow">></span> <span class="data-label">MinP:</span> <span>0.03 - 0.04</span> </div> <div class="data-row"> <span class="data-arrow">></span> <span class="data-label">TopP:</span> <span>0.9 - 1.0</span> </div> <div class="data-row"> <span class="data-arrow">></span> <span class="data-label">Dry:</span> <span>0.8, 1.75, 4</span> </div> </div> <h3 class="subheading">Instruct</h3> <div class="data-box"> <p style="margin: 0;">Llama-3-Instruct-Names but you will need to uncheck "System same as user".</p> </div> </div> </div> <div class="section-container"> <div class="section-header"> <div class="section-indicator"></div> <h2 class="section-title">03 // QUANTIZATIONS</h2> </div> <div class="section-content"> <div style="margin-bottom: 20px;"> <h3 class="subheading">GGUF</h3> <div style="margin-left: 20px;"> <span style="color: #33ff99; display: inline-block; margin-right: 10px;">> </span><a href="https://huggingface.co/mradermacher/L3.3-GeneticLemonade-Unleashed-v3-70B-i1-GGUF">iMatrix (Mradermacher)</a><br> </div> </div> <div> <h3 class="subheading">EXL2</h3> <div style="margin-left: 20px;"> <span style="color: #33ff99; display: inline-block; margin-right: 10px;">> </span><a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B_4bpw-hb6-exl2">4bpw</a><br> <span style="color: #33ff99; display: inline-block; margin-right: 10px;">> </span><a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B_4.5bpw-hb6-exl2">4.5bpw</a><br> <span style="color: #33ff99; display: inline-block; margin-right: 10px;">> </span><a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B_6bpw-hb8-exl2">6bpw</a> </div> </div> </div> </div> <div class="section-container"> <div class="section-header"> <div class="section-indicator"></div> <h2 class="section-title">04 // TRAINING PROCESS</h2> </div> <div class="section-content"> <p>The model first went through SFT with a small synthetic dataset of 2.9 million tokens, approximately 750 conversations. Primarily RP data with small amounts of random instruct / assistant data and creative writing.</p> <p>The model then went through DPO training using approx 1100 chosen examples from the SFT dataset that were of exceptional quality or showed verifiable instruction following. Rejected samples were generated using another Llama 3.3 finetune that is known for poor instruction following.</p> </div> </div> </div> <h3 class="subheading">Axolotl configs</h3> <p>Neither are optimized for cost / performance efficiency, YMMV.</p> <h3>SFT 1*H200</h3>

# ====================
# MODEL CONFIGURATION
# ====================
base_model: zerofata/L3.3-GeneticLemonade-Unleashed-70B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
special_tokens:
  pad_token: "<|finetune_right_pad_id|>"
chat_template: llama3

# ====================
# DATASET CONFIGURATION
# ====================
datasets:
  - path: ./dataset.jsonl
    type: chat_template
    split: train
    chat_template_strategy: tokenizer
    field_messages: messages
    message_property_mappings:
      role: role
      content: content
    roles:
      user: ["user"]
      assistant: ["assistant"]
      system: ["system"]

test_datasets:
  - path: ./validate_dataset.jsonl
    type: chat_template
    split: train
    chat_template_strategy: tokenizer
    field_messages: messages
    message_property_mappings:
      role: role
      content: content
    roles:
      user: ["user"]
      assistant: ["assistant"]
      system: ["system"]

dataset_prepared_path:
train_on_inputs: false  # Only train on assistant responses

# ====================
# QLORA CONFIGURATION
# ====================
adapter: qlora
load_in_4bit: true
lora_r: 64
lora_alpha: 128
lora_dropout: 0.1
lora_target_linear: true
# lora_modules_to_save:  # Uncomment only if you added NEW tokens

# ====================
# TRAINING PARAMETERS
# ====================
num_epochs: 2
micro_batch_size: 4
gradient_accumulation_steps: 2
learning_rate: 1.5e-5
optimizer: paged_adamw_8bit
lr_scheduler: rex
warmup_ratio: 0.05
weight_decay: 0.01
max_grad_norm: 1.0

# ====================
# SEQUENCE & PACKING
# ====================
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

# ====================
# HARDWARE OPTIMIZATIONS
# ====================
bf16: auto
flash_attention: true
gradient_checkpointing: true

# ====================
# EVALUATION & CHECKPOINTING
# ====================
evaluation_strategy: steps
eval_steps: 5
save_strategy: steps
save_steps: 5
save_total_limit: 5  # Keep best + last few checkpoints
load_best_model_at_end: true
metric_for_best_model: eval_loss
greater_is_better: false
early_stopping_patience: 5

# ====================
# LOGGING & OUTPUT
# ====================
output_dir: ./output_model
logging_steps: 2
save_safetensors: true

# ====================
# WANDB TRACKING
# ====================
wandb_project: project_name
# wandb_entity: your_entity
# wandb_name: your_run_name

<h3>DPO 2*H200</h3>

# ====================
# MODEL CONFIGURATION
# ====================
base_model: ApocalypseParty/unleashed-fulldata30
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
special_tokens: {}
chat_template: tokenizer_default

# ====================
# RL/DPO CONFIGURATION
# ====================
rl: dpo
rl_beta: 0.07

# ====================
# DATASET CONFIGURATION
# ====================
datasets:
  - path: ./dpo_cleaned-v3_deduplicated.jsonl
    type: chat_template.default
    field_messages: conversation
    field_chosen: chosen
    field_rejected: rejected
    message_property_mappings:
      role: role
      content: content
    roles:
      system: ["system"]
      user: ["user"]
      assistant: ["assistant"]
dataset_prepared_path:
train_on_inputs: false  # Only train on assistant responses

# ====================
# QLORA CONFIGURATION
# ====================
adapter: qlora
load_in_4bit: true
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
# lora_modules_to_save:  # Uncomment only if you added NEW tokens

# ====================
# TRAINING PARAMETERS
# ====================
num_epochs: 1
micro_batch_size: 4
gradient_accumulation_steps: 2
learning_rate: 2e-6
optimizer: adamw_8bit
lr_scheduler: cosine
warmup_steps: 5
weight_decay: 0.01
max_grad_norm: 1.0

# ====================
# SEQUENCE CONFIGURATION
# ====================
sequence_len: 4096
pad_to_sequence_len: true

# ====================
# HARDWARE OPTIMIZATIONS
# ====================
bf16: auto
tf32: false
flash_attention: true
gradient_checkpointing: offload
deepspeed: deepspeed_configs/zero1.json

# ====================
# CHECKPOINTING
# ====================
save_steps: 10
save_total_limit: 10
load_best_model_at_end: true
metric_for_best_model: eval_loss
greater_is_better: false

# ====================
# LOGGING & OUTPUT
# ====================
output_dir: ./dpo_model
logging_steps: 2
save_safetensors: true

# ====================
# WANDB TRACKING
# ====================
wandb_project: project_name
# wandb_entity: your_entity
# wandb_name: your_run_name

</body> </html>