zerofata
/

L3.3-GeneticLemonade-Unleashed-v3-70B_4bpw-hb6-exl2

+---
+base_model:
+- zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B
+library_name: transformers
+license: llama3
+---
+<!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>
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c6c638328850e12d38c/_XKaHDAVin1ZkdlHyh09q.png)
+  <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.</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 - 1.0</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="">iMatrix</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>
+```yml
+# ====================
+# 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>
+```yml
+# ====================
+# 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>