README.md

---
library_name: transformers
license: cc-by-nc-4.0
tags:
- creative-writing
- creative-writer
- multiplicative-lora
---

An experimental model, fine-tuned using the ["multiplicative-LoRA" method](#the-multiplicative-lora-method) on [c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01).

Other experimental models, based off `creative-writer-v0.1-alfa-35b` that attempt to encourage more diverse/creative text generation:

- [creative-writer-v0.1-bravo-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-bravo-35b) - Scaled the pre-softmax logits by `1.1` during training (and then reset after training).
- [creative-writer-v0.1-charlie-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-charlie-35b) - Scaled the pre-softmax logits by `0.9` during training (and didn't reset after training).
- [creative-writer-v0.1-delta-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-delta-35b) - Trained using [Focal Loss](https://arxiv.org/abs/1708.02002) with `gamma=2` (instead of stock [Cross Entropy Loss](https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html)).

---

# The "multiplicative-LoRA" method

Uses:

`h = (I + lora_B @ lora_A) @ tensor @ x = tensor @ x + lora_B @ lora_A @ tensor @ x`

instead of the normal "addative-LoRA" method of:

`h = (tensor + lora_B @ lora_A) @ x = tensor @ x + lora_B @ lora_A @ x`

I only apply this to the `down_proj` matrices, and skip the last layer's `down_proj` matrix in the same way as [creative-writing-control-vectors-v3.0](https://huggingface.co/jukofyork/creative-writing-control-vectors-v3.0).

This currently requires hacking [PEFT's layer.py](https://github.com/huggingface/peft/blob/main/src/peft/tuners/lora/layer.py) like so:

```python
#self.lora_A[adapter_name] = nn.Linear(self.in_features, r, bias=False)
self.lora_A[adapter_name] = nn.Linear(self.out_features, r, bias=False)
self.lora_B[adapter_name] = nn.Linear(r, self.out_features, bias=False)
```

and:

```python
#x = x.to(lora_A.weight.dtype)
temp = result.to(lora_A.weight.dtype)

if not self.use_dora[active_adapter]:
    #result = result + lora_B(lora_A(dropout(x))) * scaling
    result = result + lora_B(lora_A(dropout(temp))) * scaling
```

Then to merge you need to hack [qlora-pipe's merge_lora.py](https://github.com/tdrussell/qlora-pipe/blob/main/merge_lora.py) to use:

```python
old_type = tensor.dtype
tensor = tensor.to(torch.float32)
tensor += scale * lora_B.to(torch.float32) @ lora_A.to(torch.float32) @ tensor
tensor = tensor.to(old_type)
```

---

# Training

- Took just under 4 days using dual-A6000 GPUs connected via NVLink, using [qlora-pipe](https://github.com/tdrussell/qlora-pipe).
- The dataset consisted of approximately 1000 pre-2012 books converted to Markdown (~180M tokens) using the same `dataset_combination_mode = 'concatenate'` as [Llama-3-70B-Instruct-Storywriter](https://huggingface.co/tdrussell/Llama-3-70B-Instruct-Storywriter).

## `config_creative_writer.toml`

```toml
# Paths
model = '/mnt/data/c4ai-command-r-v01'
output_dir = '/mnt/data/creative-writer-v0.1-alfa-35b'

# Lora configuration
lora_rank = 64
lora_alpha = 64
lora_dropout = 0.0
target_modules = ['down_proj']
layers_to_transform = '0:38'  # skip last layer

# Optimization configuration
epochs = 1
lr_scheduler = 'constant'
warmup_steps = 100
batch_size_tokens = 8192

# Performance settings
pipeline_stages = 2
logging_steps = 1
eval_steps = 100
save_steps = 100
checkpoint_every_n_minutes = 60
eval_before_first_step = true
model_weight_dtype = 'bfloat16'
lora_weight_dtype = 'bfloat16'
keep_states = 3
group_by_length = true
activation_checkpointing = 'unsloth'

# Resume a prior run
resume_from_checkpoint = false

# Dataset configuration
dataset_combination_mode = 'concatenate'
eval_gradient_accumulation_steps = 1

[optimizer]
type = 'adamw_kahan'
lr = 5e-6
beta1 = 0.9
beta2 = 0.99
weight_decay = 0.01

[[datasets]]
name = 'books'
dataset_type = 'textfile'
dataset_path = '/mnt/data/datasets/ebooks/*.txt'
sequence_len = 8192
eval_size = 0.01
```

## `ds_creative_writer.json`

```json
{
    "train_micro_batch_size_per_gpu": 1,
    "gradient_accumulation_steps": 16,
    "gradient_clipping": 1.0,
    "steps_per_print": 1
}
```