Experimental model focused on RP and storytelling. This method attempts to bring some of the intrigue and style of the base model back into the instruct model.

This is a model trained in four stages (Use with Llama-8B-Instruct or Llama-8B-Instruct abliterations)


Base Model -- 1 Gig of semi-structured pretraining data (Uniform distribution centered around 4096 ctx length, b/w 512-8192)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/637f3b03932a61b89aefbf5c/hpdbVRrM1yt65-gNtRIfT.png)
- Base pretraining phase 1 (Constant LR, text completion -- 20,000 steps 2/3 epoch)
- Base pretraining phase 2 (Cosine LR, text completion -- 10,000 steps 1/3 epoch)


Merge LORA into instruct model -- 100 MB of structured story-instruct data (All samples attempt to be near 8192 ctx fullsize instructions)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/637f3b03932a61b89aefbf5c/V1Jf07k8JdI0_OzIDc7FF.png)
- Story-instruct tune phase 1 (Constant LR, ~1250 steps, 1 epoch)
- Story-instruct tune phase 2 (Cosine LR, ~1250 steps, 1 epoch)

Trained using <https://github.com/unslothai/unsloth>
Rough script:
```python
model = FastLanguageModel.get_peft_model(
    model,
    r = 64,
    target_modules = ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    lora_alpha = 32,
    lora_dropout = 0.05, # 0 for base pretraining
    bias = "none",
    use_gradient_checkpointing = "unsloth",
    random_state = 3407,
    max_seq_length = max_seq_length,
    use_rslora = True,
    loftq_config = None,
)

trainer = SFTTrainer(
    model = model,
    train_dataset = train_dataset,
    dataset_text_field = "text",
    max_seq_length = max_seq_length,
    tokenizer = tokenizer,
    args = TrainingArguments(
        per_device_train_batch_size = 2,
        warmup_steps = 45,
        num_train_epochs=2, #1 for base-pretraining
        fp16 = not torch.cuda.is_bf16_supported(),
        bf16 = torch.cuda.is_bf16_supported(),
        logging_steps = 15,
        logging_dir="logs",
        report_to="tensorboard",
        output_dir = "outputs",
        save_strategy=IntervalStrategy.STEPS,
        save_steps=100,
        save_total_limit=30,
        optim = "adamw_torch_fused",
        lr_scheduler_type="cosine", # <- Changed over time
        learning_rate=5e-5,
        weight_decay=0.10, # .15 for base pretraining
        adam_beta1=0.88, # .9 for base pretraining
        adam_beta2=0.99,  # .999 for base pretraining
    ),
)
```