mirror of
https://github.com/unslothai/unsloth.git
synced 2026-08-25 00:33:49 +00:00
3177523091
* Render a static prefix when default_system_message is None
A chat template can start with a preamble that has no {SYSTEM} placeholder.
construct_chat_template emitted it only from the
{% if messages[0]['role'] == 'system' %} arm, and with no {SYSTEM} slot that
arm is unreachable: a caller system message hits the loop's raise_exception
instead. So the preamble rendered in no successful conversation at all.
The Ollama modelfile returned by the same call still contains it, so training
text built from the Jinja template lacked the prefix the served model was
later prompted with:
trained on : '### User: Hi\n### Assistant: Yo</s>'
served : 'Below are some instructions that describe some tasks.\n\n...'
Give that branch the same {% else %} arm the default_system_message path
gets. Both arms are then identical literals, so the existing 'system part is
the same' regex folds them into one unconditional emit, and a caller-supplied
system message still reaches raise_exception, which is what #7199 intended.
Only templates with a static prefix and default_system_message=None change:
across 21 combinations of system part and default message, the other 18
produce byte-identical Jinja and every modelfile is unchanged.
* Shorten static preamble comments
* Keep BOS-only prefixes role-strict
---------
Co-authored-by: Wasim Yousef Said <wasimysdev@gmail.com>
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| conftest.py | ||
| test_bitsandbytes_kernel_readiness.py | ||
| test_change_system_message.py | ||
| test_conftest_bitsandbytes_preimport.py | ||
| test_construct_chat_template_validation.py | ||
| test_cpo_processor_text_tokenizer.py | ||
| test_cross_platform_parity.py | ||
| test_dpo_vision_processor_passthrough.py | ||
| test_e2e_no_torch_sandbox.py | ||
| test_fast_language_model_text_only.py | ||
| test_fast_model_config_passthrough.py | ||
| test_fast_sentence_transformer_embedding_parity.py | ||
| test_fast_sentence_transformer_redirect_lifecycle.py | ||
| test_flash_attn_install_python_stack.py | ||
| test_get_chat_template_escaping.py | ||
| test_get_lora_parameters_bias_fp8_block_size.py | ||
| test_get_lora_parameters_fp8_block_size.py | ||
| test_gpu_init_ldconfig_guard.py | ||
| test_grpo_ddp_model_config.py | ||
| test_import_without_bitsandbytes.py | ||
| test_install_python_stack.py | ||
| test_install_uv_override_space.py | ||
| test_mlx_public_trainer_api.py | ||
| test_no_torch_filtering.py | ||
| test_orpo_processor_text_tokenizer.py | ||
| test_pad_token_fix.py | ||
| test_patch_trl_rl_trainers_defensive.py | ||
| test_remove_special_tokens_no_bos.py | ||
| test_revision_forwarding.py | ||
| test_studio_import_no_torch.py | ||
| test_studio_runtime_gate.py | ||
| test_to_sharegpt_optional_none.py | ||
| test_tokenizers_and_torch_constraint.py | ||
| test_torchcodec_torch_compat.py | ||
| test_unsloth_run_tool_policy_resolver.py | ||
| test_v100_fullft_precision.py | ||
| test_virustotal_scan.py | ||
| test_vision_lora_targeting.py | ||
| test_windows_arm64_python_choice.py | ||
| test_windows_git_gate.py | ||
| test_windows_installer_concurrency_guard.py | ||
| test_windows_no_torch_setup.py | ||
| test_windows_python_313_8_screen.py | ||
| test_windows_python_venv_hardening.py | ||
| test_windows_setup_output_encoding.py | ||
| test_windows_studio_update_launcher.py | ||
| test_windows_vcredist_download_tls.py | ||