Initial SQL-only 1C adapter baseline

This commit is contained in:
2026-07-22 03:03:47 +03:00
commit e2503b77e7
545 changed files with 184711 additions and 0 deletions
@@ -0,0 +1,35 @@
id: qwen3-4b-1c-lora-v1
base_model_path: /models/base/qwen3-4b-instruct-2507
dataset_path: /workspace/plugins/1c/training/prepared/train.chat.jsonl
output_dir: /models/adapters/1c/qwen3-4b-1c-lora-v1
max_seq_length: 2048
train:
num_train_epochs: 3
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.0002
warmup_ratio: 0.03
logging_steps: 1
save_strategy: "no"
save_total_limit: 1
bf16: true
fp16: false
lora:
r: 16
lora_alpha: 32
lora_dropout: 0.05
bias: none
target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
quantization:
load_in_4bit: true
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: true
bnb_4bit_compute_dtype: bfloat16
notes: "Training config for the first 1C LoRA adapter. Requires complete base model and GPU host."