NOTE: Read the Control Adapter documentation for implementation details.

Trained via qlora-pipe-lite:

# ==============================
# MODEL AND OUTPUT CONFIGURATION
# ==============================

model_dir = '/mnt/models/command-a-03-2025-uncut'
output_dir = '/mnt/fiction_finetunes/finetuned'

# ===========================
# TRAINING TYPE CONFIGURATION
# ===========================

use_control_adapters = true

load_in_4bit = true

# =============================
# CONTROL ADAPTER CONFIGURATION
# =============================

# ~20 tokens per trainable parameter (1e9/(64*64*(12288+1)))
lora_rank = 64

control_adapter_gamma = 0.1

# =======================
# OPTIMIZER CONFIGURATION
# =======================

lr = 1e-3

# ======================
# TRAINING CONFIGURATION
# ======================

sequence_len = 4096

pipeline_stages = 2

# 120 batch size (3*40) --> 480k tokens per step (4096*120)
gradient_accumulation_steps = 40

use_column_major_topology = true

# =====================
# DATASET CONFIGURATION
# =====================

sequence_prefix = 5                 # "<BOS_TOKEN>"

document_prefix = [255000, 255007]  # "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>"
document_suffix = 255001            # "<|END_OF_TURN_TOKEN|>"

mask_tokens = true                  # Mask all special tokens

drop_tails = true

mix_datasets = true

# -------------------
# POSITIVE CLASS DATA
# -------------------

[[datasets]]
dataset_path = '/mnt/datasets/books-fiction-paragraphs/*.json'
control_class = 1

# -------------------
# NEGATIVE CLASS DATA
# -------------------

[[datasets]]
dataset_path = '/mnt/datasets/slop-fiction-paragraphs/*.json'
control_class = -1

using ~1B tokens (ie: ~500M positive and ~500M negative) from:

jukofyork/books-fiction-paragraphs (NOTE: I have not uploaded this, but you can use my jukofyork/gutenberg-fiction-paragraphs to get similar results...)
jukofyork/slop-fiction-paragraphs

taking around 15 days using 6x RTX A6000 over 3 machines:

(hence the 120 batch size: (num_gpus / pipeline_stages) * gradient_accumulation_steps = (6 / 2) * 40 = 120)

NOTE: Ignore the 22.69 days - it crashed whilst I was away from home and had to be restarted a week later...

The control adapter was then converted to a LoRA using control_adapter_to_lora.py:

command-a-03-2025-writer-v1-lora

and then merged using the merge-lora space:

✓ Successfully merged and uploaded model!
Model URL: https://huggingface.co/jukofyork/command-a-03-2025-writer-v1
Scale factor: 1
Processed 49 shards
Merged 128 layers with LoRA weights

See command-a-03-2025-writer-v1-lora-gguf for a LoRA in GGUF format that can be used with the --lora option on top of the base command-a-03-2025-uncut to get the same effect.