Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Python cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llmloralow-vrammachine-learningollamapeftpythonpytorchqlorasfttransformers
docs(contributors): #2175 [skip ci]
Alpamys13cef1bc81b2
diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.mdindex 88659d03..71180b77 100644--- a/CONTRIBUTORS.md+++ b/CONTRIBUTORS.md@@ -944,6 +944,7 @@ Listed by first contribution. PR numbers link the work.- Took #2047: GRPO could only score with a rule, so a task with no checkable answer had no scorer. They posted the plan first, took the maintainer's twelve corrections, then added `training.reward_fn: judge_rank`: one judge call sees all `num_generations` completions of a prompt, in a fresh seeded order, and the group scores `None` instead of 0.0 when the judge gives no usable answer. A required `grpo_judge_max_calls` is checked after the data loads and before the model does, and failed or all-equal groups are logged under `judge/`. **The part worth copying is the questions**: the PR lists the five choices it made without a ruling and the one mutation that survives, and the follow-up commit closed that survivor by deleting the dead flag instead of arguing for it. ([#2047](https://github.com/MakazhanAlpamys/Soup/issues/2047), [#2117](https://github.com/MakazhanAlpamys/Soup/pull/2117))- Took item 3 of #797 (the issue stays open for the vision/audio k-bit test): `training.gradient_checkpointing: true` or a tier did nothing on `distill`, `classifier`, `asr` and `unlearn`, which never read it. They passed it to the HF arguments of the first three and, for unlearn's own loop, called `gradient_checkpointing_enable()` on the LoRA policy model, with tests that drive each real `setup()` on CPU and count the backward recompute, and a table of opposite-value mutations per site. 36 tests (26 fail on `main`), 10 of 10 mutations killed by named tests, and the adapter weights and first-step loss check out with checkpointing on. ([#797](https://github.com/MakazhanAlpamys/Soup/issues/797), [#2140](https://github.com/MakazhanAlpamys/Soup/pull/2140))- Fixed the `expandable_segments` allocator hint never being applied to a streamed `soup train` on Linux: `detect_device()` started CUDA before the code that would set the variable ran, so every streamed CUDA run printed "not enabled" and the hint was lost. The hint is now set from `train.py` before device detection (streamed runs on Linux and WSL2 only, an exported value kept, an empty one counted as unset), and the reason line names the variable when another value is the cause. Verified on a WSL2 card by @abdulwaarith0 and with a recorder at `detect_device` on CPU; 12 of 12 source mutations killed ([#2149](https://github.com/MakazhanAlpamys/Soup/issues/2149), [#2156](https://github.com/MakazhanAlpamys/Soup/pull/2156))+ - Hardened the gradient-checkpointing tests for distill, classifier, asr and unlearn: the step must change a trainable weight, and asr is covered with asr_lora ([#797](https://github.com/MakazhanAlpamys/Soup/issues/797), [#2175](https://github.com/MakazhanAlpamys/Soup/pull/2175))- **Nariman Abdikarim** ([@Nari-Ab](https://github.com/Nari-Ab))- Sanitized model and dataset paths across CLI display sinks and both short-name branches, with 17 portable regressions covering refusals, adapter loading, saved outputs and real Elo/leaderboard table consumers. Independent maintainer validation passed all 17 cases before and after five source undos that caused 1/1/1/3/4 failures; all eight required hosted checks passed ([#1864](https://github.com/MakazhanAlpamys/Soup/issues/1864), [#1868](https://github.com/MakazhanAlpamys/Soup/pull/1868))