par zerofata
Open source · 652k downloads · 11 likes
L3.3 GeneticLemonade Final v2 70B est un modèle de langage avancé spécialisé dans la génération de texte créatif et technique, alliant puissance et originalité. Conçu pour exceller dans les tâches complexes comme la rédaction, l'analyse ou la synthèse, il se distingue par sa capacité à produire des réponses nuancées et contextuellement riches, tout en intégrant une touche d'innovation algorithmique. Ses cas d'usage couvrent aussi bien l'assistance à la création de contenu que l'aide à la décision, le prototypage d'idées ou l'exploration de concepts interdisciplinaires. Ce qui le rend unique, c'est son approche "génétique", optimisée pour évoluer et s'adapter à des besoins variés avec une efficacité remarquable. Son équilibre entre performance brute et flexibilité en fait un outil polyvalent pour les professionnels et les créatifs.
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.
Play with these, they are not the 'best' settings just a stable baseline.
Llama-3-Instruct-Names but you will need to uncheck "System same as user".
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.
Not optimized for cost / performance efficiency, YMMV.
# ====================
# 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