---
library_name: transformers
base_model:
  - nbeerbower/llama-3-sauce-v1-8B
datasets:
- ResplendentAI/NSFW_RP_Format_NoQuote
license: other
license_name: llama3
tags:
  - nsfw
  - not-for-all-audiences
  - experimental
---

# llama-3-dragonmaid-8B

This model is based on Llama-3-8b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)

[llama-3-dragon-bophades-8B](https://huggingface.co/nbeerbower/nbeerbower/llama-3-dragon-bophades-8B) finetuned on [ResplendentAI/NSFW_RP_Format_NoQuote](https://huggingface.co/datasets/ResplendentAI/NSFW_RP_Format_NoQuote).

### Method

Finetuned using an L4 on Google Colab.

[Fine-Tune Your Own Llama 2 Model in a Colab Notebook](https://mlabonne.github.io/blog/posts/Fine_Tune_Your_Own_Llama_2_Model_in_a_Colab_Notebook.html)

### Configuration

LoRA, model, and training settings:

```python
training_arguments = TrainingArguments(
    learning_rate=2e-4,
    lr_scheduler_type="linear",
    num_train_epochs=10,
    per_device_train_batch_size=10,
    per_device_eval_batch_size=10,
    gradient_accumulation_steps=1,
    evaluation_strategy="steps",
    eval_steps=0.2,
    logging_steps=1,
    optim="paged_adamw_8bit",
    warmup_steps=10,
    report_to="wandb",
    output_dir="./results",
)

trainer = SFTTrainer(
    model=model,
    train_dataset=dataset,
    eval_dataset=dataset.select(range(0,20)),
    peft_config=peft_config,
    dataset_text_field="input",
    max_seq_length=2048,
    tokenizer=tokenizer,
    args=training_arguments,
)
```