v0.1.9

## What's Changed
* Add QwQ full fine-tune and QLoRA configs by @wizeng23 in https://github.com/oumi-ai/oumi/pull/1518
* Update TRL to 0.15 and fix Liger/dataset code by @wizeng23 in https://github.com/oumi-ai/oumi/pull/1507
* [tiny] Remove vLLM Colab link and fix Alpaca Eval quickstart by @wizeng23 in https://github.com/oumi-ai/oumi/pull/1530
* Evaluation: Inference optimizations by @kaisopos in https://github.com/oumi-ai/oumi/pull/1522
* Qwen2.5 VL: Replace "from source" install with `transformers>=0.49` by @nikg4 in https://github.com/oumi-ai/oumi/pull/1528
* [Evaluation] Renaming `evaluation_platform` → `evaluation_backend` by @kaisopos in https://github.com/oumi-ai/oumi/pull/1526
* [tiny] Clean up datasets code by @wizeng23 in https://github.com/oumi-ai/oumi/pull/1529
* Minor logging improvements in `BaseMapDataset` by @nikg4 in https://github.com/oumi-ai/oumi/pull/1532
* Upload scripts used in a Weekly Walkthrough by @taenin in https://github.com/oumi-ai/oumi/pull/1533
* Update VisionLanguageConversationFeatureGenerator by @nikg4 in https://github.com/oumi-ai/oumi/pull/1531
* [docs] add security.md by @oelachqar in https://github.com/oumi-ai/oumi/pull/1534
* [Evaluation] Custom evaluation notebook: a reliability classifier by @kaisopos in https://github.com/oumi-ai/oumi/pull/1535
* Multimodal: Limit max number of images per Conversation by @nikg4 in https://github.com/oumi-ai/oumi/pull/1536
* Auto-populate and validate params specific to `vision_language_sft` collator in `TrainingConfig` by @nikg4 in https://github.com/oumi-ai/oumi/pull/1537
* Update Oumi Env to use Rich formatting by @taenin in https://github.com/oumi-ai/oumi/pull/1541
* Update oumi launch to use Rich formatting by @taenin in https://github.com/oumi-ai/oumi/pull/1543
* Update oumi evaluate to use rich formatting. by @taenin in https://github.com/oumi-ai/oumi/pull/1544
* Update the CLI to replace all prints with Rich prints. by @taenin in https://github.com/oumi-ai/oumi/pull/1547
* Render the oumi env command as a shell block in bug reports. by @taenin in https://github.com/oumi-ai/oumi/pull/1548
* Define `Conversation` proto bufs by @nikg4 in https://github.com/oumi-ai/oumi/pull/1550
* [Evaluation] Modifying Alpaca Eval results format to be consistent with LM Harness by @kaisopos in https://github.com/oumi-ai/oumi/pull/1551
* Augmenting logging training/model statistics  by @optas in https://github.com/oumi-ai/oumi/pull/1545
* Misc no-op code cleanups by @nikg4 in https://github.com/oumi-ai/oumi/pull/1553
* Add code used for the evaluation demo. by @taenin in https://github.com/oumi-ai/oumi/pull/1556
* Add `OUMI_FORCE_EDITABLE_INSTALL` env var to do editable Oumi install from source in job configs by @wizeng23 in https://github.com/oumi-ai/oumi/pull/1420
* Add letter counting GRPO example by @wizeng23 in https://github.com/oumi-ai/oumi/pull/1539
* Remove UV install from notebooks as this breaks colab by @taenin in https://github.com/oumi-ai/oumi/pull/1558
* [Evaluation] Updates in hallucination notebook by @kaisopos in https://github.com/oumi-ai/oumi/pull/1552
* [Evaluations] Custom evals: Adding support for `eval_kwargs` by @kaisopos in https://github.com/oumi-ai/oumi/pull/1557
* Logging message update in `log_number_of_model_parameters` by @nikg4 in https://github.com/oumi-ai/oumi/pull/1560
* [Evaluation][Custom] Removing restrictions and better error checking by @kaisopos in https://github.com/oumi-ai/oumi/pull/1561
* Support text truncation (`max_length`) for `vision_language_sft` collator by @nikg4 in https://github.com/oumi-ai/oumi/pull/1559
* phi 4 multimodal training version 1 ( with limitations ) by @optas in https://github.com/oumi-ai/oumi/pull/1555
* Phi-4 basic inference with native/vllm by @optas in https://github.com/oumi-ai/oumi/pull/1563
* [minor] phi4 train improvements by @optas in https://github.com/oumi-ai/oumi/pull/1564
* Fix printing errors in oumi env for non-string values. by @taenin in https://github.com/oumi-ai/oumi/pull/1565


**Full Changelog**: https://github.com/oumi-ai/oumi/compare/v0.1.8...v0.1.9