Releases: huggingface/lighteval
v0.3.0
Release Note
This introduced the new extended tasks feature, documentation and many other patches for improved stability.
New tasks are also introduced:
- Big Bench Hard: https://huggingface.co/papers/2210.09261
- AGIEval: https://huggingface.co/papers/2304.06364
- TinyBench:
- MT Bench: https://huggingface.co/papers/2306.05685
- AlGhafa Benchmarking Suite: https://aclanthology.org/2023.arabicnlp-1.21/
MT-Bench marks the introduction of multi-turn prompting as well as llm-as-a-judge metric.
New tasks
- Add BBH by @clefourrier in #7, @bilgehanertan in #126
- Add AGIEval by @clefourrier in #121
- Adding TinyBench by @clefourrier in #104
- Adding support for Arabic benchmarks : AlGhafa benchmarking suite by @alielfilali01 in #95
- Add mt-bench by @NathanHB in #75
Features
- Extended Tasks ! by @clefourrier in #101, @lewtun in #108, @NathanHB in #122, #123
- Added support for launching inference endpoint with different model dtypes by @shaltielshmid in #124
Documentation
- Adding LICENSE by @clefourrier in #86, @NathanHB in #89
- Make it clearer in the README that the leaderboard uses the harness by @clefourrier in #94
Small patches
- Update huggingface-hub for compatibility with datasets 2.18 by @clefourrier in #84
- Tidy up dependency groups by @lewtun in #81
- bump git python by @NathanHB in #90
- Sets a max length for the MATH task by @clefourrier in #83
- Fix parallel data processing bug by @clefourrier in #92
- Change the eos condition for GSM8K by @clefourrier in #85
- Fixing rolling loglikelihood management by @clefourrier in #78
- Fixes input length management for generative evals by @clefourrier in #103
- Reorder addition of instruction in chat template by @clefourrier in #111
- Ensure chat models terminate generation with EOS token by @lewtun in #115
- Fix push details to hub by @NathanHB in #98
- Small fixes to InferenceEndpointModel by @shaltielshmid in #112
- Fix import typo autogptq by @clefourrier in #116
- Fixed the loglikelihood method in inference endpoints models by @clefourrier in #119
- Fix TextGenerationResponse import from hfh by @Wauplin in #129
- Do not use deprecated list_files_info by @Wauplin in #133
- Update test workflow name to 'Tests' by @Wauplin in #134
New Contributors
- @shaltielshmid made their first contribution in #112
- @bilgehanertan made their first contribution in #126
- @Wauplin made their first contribution in #129
Full Changelog: v0.2.0...v0.3.0
v0.2.0
Release Note
This release focuses on customization and personalisation: it's now possible to define custom metrics, not just custom tasks, see the README for the full mechanism.
Also includes small fixes to improve stability and new tasks. We made the choice to split community tasks from the main library source to better manage maintenance.
Better community task handling
- New mechanism for evaluation contributions by @clefourrier in #47
- Adding the custom metrics system by @clefourrier in #65
New tasks
- Add GPQA by @clefourrier in #42
- Adding support for Arabic benchmarks : AceGPT benchmarking suite by @alielfilali01 in #44
- IFEval by @clefourrier in #48
Features
- Add an automatic system to compute average for tasks with subtasks by @clefourrier in #41
small patches
- Typos #27, #28, #30, #29, #34,
- Better README #26, #37, #55,
- Patch fix to match with config update/simplification in nanotron by @thomwolf in #35
- bump transformers to 4.38 by @NathanHB in #46
- Small fix to be able to use extensions of nanotron configs by @thomwolf in #58
- Remove the eos token override in the Default Config Task by @clefourrier in #54
- Update leaderboard task set by @lewtun in #60
- Remove the eos token override in the Default Config Task by @clefourrier in #54
- Fixes wikitext prompts + some patches on tg models by @clefourrier in #64
- Fix unset generation size by @clefourrier in #76
- Update ruff by @clefourrier in #71
- Relax sentencepiece version by @lewtun in #74
- Better chat template system by @clefourrier in #38
✨ Community Contributions
- @ledrui made their first contribution in #26
- @alielfilali01 made their first contribution in #44
- @lewtun made their first contribution in #55
Full Changelog: v0.1.1...v0.2.0
v0.1.1
v0.1.0
Init
LightEval 🌤️
A lightweight LLM evaluation
Context
LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
We're releasing it with the community in the spirit of building in the open.
Note that it is still very much early so don't expect 100% stability ^^'
In case of problems or question, feel free to open an issue!
Full Changelog: https://github.com/huggingface/lighteval/commits/v0.1