Add GLM5 SFT support

[samaritan1998]

Summary

• Add a GLM5-specific SFT loss mask type that follows GLM-style stop markers.
• Add a GLM5 SFT launch script using sft_loss and the existing GLM5 Megatron model config.
• Add unit coverage for multi-turn GLM5 masking, tool calls, and step_loss_mask handling.

Details

The GLM5 mask generation renders the full chat template, supervises assistant spans, and treats <|user|>, <|observation|>, and <|endoftext|> as stop boundaries. This mirrors ms-swift's GLM5/GLM4.7 behavior, where <|user|> is the suffix used to teach the model to stop instead of appending tokenizer EOS.

Validation

• Ran GLM5 mask tests and adjacent Qwen3.5 mask tests via direct Python invocation with a lightweight transformers stub, because this local environment does not have pytest or transformers installed.
• bash -n scripts/run-glm5-744B-A40B-sft.sh
• git diff --check

[samaritan1998]

Local validation passed for GLM5 loss mask behavior and script syntax.