# L3.3-GeneticLemonade-Final-v2-70B **Repository Path**: hf-models/L3.3-GeneticLemonade-Final-v2-70B ## Basic Information - **Project Name**: L3.3-GeneticLemonade-Final-v2-70B - **Description**: Mirror of https://huggingface.co/zerofata/L3.3-GeneticLemonade-Final-v2-70B - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-11-30 - **Last Updated**: 2025-11-30 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README --- library_name: transformers license: llama3 datasets: - zerofata/Roleplay-Anime-Characters - zerofata/Instruct-Anime-CreativeWriting - zerofata/Summaries-Anime-FandomPages base_model: - zerofata/L3.3-GeneticLemonade-Final-70B --- GENETIC LEMONADE FINAL v2

GENETIC LEMONADE

FINAL v2
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c6c638328850e12d38c/0Ka08CdFUIJtYctBeBATo.png)

01 // OVERVIEW

Wasn't intending to release another model (so soon at least), but I was testing out some new dataset ideas and thought this model came out pretty nice.

zerofata/GeneticLemonade-Final SFT QLora finetune.

This is an uncensored creative model intended to excel at character driven RP / ERP.

This model is designed to provide longer, narrative heavy responses where characters are portrayed accurately and proactively.

Compared to Unleashed v3, this model has significantly reduced positivity bias and arguably a nicer writing style. The tradeoff is it swipe heavy, making a few more logical errors and can be a bit too concise at times.

02 // SILLYTAVERN SETTINGS

Play with these, they are not the 'best' settings just a stable baseline.

Recommended Samplers

> Temp: 0.9 - 1
> MinP: 0.03 - 0.04
> TopP: 0.9 - 1.0
> Dry: 0.8, 1.75, 4

Instruct

Llama-3-Instruct-Names but you will need to uncheck "System same as user".

03 // QUANTIZATIONS

GGUF

> iMatrix (mradermacher)

EXL2

> 4bpw
> 4.5bpw
> 4.65bpw
> 6bpw

04 // TRAINING PROCESS

This model was trained using a dataset of approx 4.3 million tokens, 700 RP conversations, 2000 creative writing / instruct samples and about 400 summaries. The bulk of this data has been made public.

This model didn't take well to my existing DPO dataset, so it hasn't been used here.

Axolotl configs

Not optimized for cost / performance efficiency, YMMV.

SFT 1*H200

```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 ```