jukofyork/command-a-03-2025-uncut

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'
output_dir = '/mnt/finetunes/command-a-03-2025-uncut'

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

use_control_adapters = true

load_in_4bit = true

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

# ~4 tokens per trainable parameter (2e8/(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

# 30 batch size (3*10) --> 120k tokens per step (4096*30)
gradient_accumulation_steps = 10

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/instruction-responses-500MB/*.json'
control_class = 1

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

[[datasets]]
dataset_path = '/mnt/datasets/instruction-refusals-500MB/*.json'
control_class = -1

using ~200M tokens (ie: ~100M positive and ~100M negative) from:

• jukofyork/instruction-responses-500MB
• jukofyork/instruction-refusals-500MB

taking just under 4 days using 6x RTX A6000 over 3 machines:

(hence the 30 batch size: (num_gpus / pipeline_stages) * gradient_accumulation_steps = (6 / 2) * 10 = 30)

---

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

jukofyork/command-a-03-2025-uncut-lora

and then merged using the merge-lora space.

---

See https://huggingface.co/jukofyork/command-a-03-2025-uncut-lora-gguf for a LoRA in GGUF format that can be used with the --lora option on top of the base CohereLabs/c4ai-command-a-03-2025 to get the same effect.