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): #2155 [skip ci]
Alpamyscffbc4946d21
diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.mdindex b4062915..bd4908d2 100644--- a/CONTRIBUTORS.md+++ b/CONTRIBUTORS.md@@ -910,6 +910,7 @@ Listed by first contribution. PR numbers link the work.- Improved loopback Web UI host validation and IPv6 controls ([#1829](https://github.com/MakazhanAlpamys/Soup/issues/1829), [#1839](https://github.com/MakazhanAlpamys/Soup/pull/1839))- `backend: mlx` accepted `data.chat_template` and never applied it, so a prefix-stable override changed nothing and a Qwen3.5 run still died in the response-mask check after the model had loaded. They confirmed on `main` that the same config trains on the transformers backend, then refused the combination at config load with a message that names the field, the backend and both ways out, parametrised the tests over two registered names and a raw Jinja string on sft, dpo and orpo with the empty-string and unsloth controls, and removed the MLX DPO/ORPO warning and registry rows the refusal made unreachable ([#2075](https://github.com/MakazhanAlpamys/Soup/issues/2075), [#2051](https://github.com/MakazhanAlpamys/Soup/pull/2051))- `soup train` without `--yes` printed `Start training? [Y/n]:` even when nothing could answer it, so a script or a service looked hung and the message never mentioned `--yes`. They took the ruled shape (stop before the dataset loads, exit 3, a message that names `--yes`), said openly in the description that piping `y` stops working, put the check behind a `_stdin_isatty()` seam like autopilot's, wrote the `--yes` help sentence and regenerated the CLI reference, and extended the tests with controls for `--yes`, `--dry-run`, the loader and trainer never being reached, and a faked TTY ([#2077](https://github.com/MakazhanAlpamys/Soup/issues/2077), [#2052](https://github.com/MakazhanAlpamys/Soup/pull/2052))+ - Closed #2136: several readers opened user-supplied files as plain UTF-8, so a BOM-prefixed file made `json` refuse the whole document, silently dropped the first JSONL record or put U+FEFF into the first prompt. They moved fifteen read sites to `utf-8-sig`, left every writer on UTF-8, listed the four readers they deliberately left out, and pinned `soup attest verify` with real Ed25519 cases (valid, tampered, wrong key, BOM on either file). 93 tests (48 fail on `main`), and each of the 15 codec reversions fails a named test. ([#2136](https://github.com/MakazhanAlpamys/Soup/issues/2136), [#2155](https://github.com/MakazhanAlpamys/Soup/pull/2155))- **Akshat Shah** ([@akshatshahh](https://github.com/akshatshahh))- First contribution: `http://[::1]:<port>` was accepted by the judge API-base and vLLM checks but refused by eval-gate suites, `soup ship --judge-model` and the online-DPO trainer, because three gates kept their own `("localhost", "127.0.0.1")` literal and two more kept a third copy. They made all five import `net_guard.LOOPBACK_HOSTS` and added an AST ratchet that fails on any rebuilt loopback literal, including single-quoted and multi-line spellings. Their 27 tests: 11 fail on main, 27 pass here; 7 mutations, all killed ([#1548](https://github.com/MakazhanAlpamys/Soup/issues/1548), [#1554](https://github.com/MakazhanAlpamys/Soup/pull/1554))