fix(training): follow unsloth's Qwen3 guide exactly

fix(training): upgrade base image to torch 2.6.0+cu126

fix(training): pin torchao==0.5.0 after unsloth to fix torch.int1 error

fix(training): upgrade to torch 2.5.1+cu124, restore unsloth for Qwen3

fix(training): drop unsloth, use bitsandbytes+PEFT for SFT

fix(docker): pin torchao==0.5.0 + transformers/trl/peft before unsloth install

fix(docker): COPY README.md into build context (hatchling metadata requires it)

feat(training): A10G-optimised pipeline — auto train.py, Dockerfile.train, GH Action sync