0.3.2 - Error message improvements

Includes #281

0.3.1

What's Changed

• 🐛 Fix the ordering of arguments in all the stream text gen functions by @gkumbhat in #268

Full Changelog: 0.3.0...0.3.1

0.3.0

What's Changed

• Expose seed by @tharapalanivel in #201
• Refactor / Consolidate Batch Tokenization for Causal Language Modeling by @alex-jw-brooks in #192
• Validation checks by @tharapalanivel in #200
• 🐛 Align inference params order by @tharapalanivel in #204
• fix link for contributing info by @jimknochelmann in #195
• fix imports for caikit >=0.15.0 by @dtrifiro in #209
• Fix tokenization path by @gkumbhat in #202
• Add ft loss logging by @gkumbhat in #208
• ✨ Add support for reading base model from base models dir by @gkumbhat in #211
• use arg use_cpu instead of no_cuda by @alex-jw-brooks in #215
• Remove stop sequence default by @tharapalanivel in #213
• 🐛 Add support for setting random seed for prompt tuning training by @gkumbhat in #217
• Causal LM tokenization: Chunking and seq2seq Forward by @alex-jw-brooks in #206
• Resync inf params tgis by @gkumbhat in #220
• 🥅 Disallow empty train streams by @evaline-ju in #223
• ⬆️ Update caikit[runtime-grpc,runtime-http] requirement from <0.21.0,>=0.18.1 to >=0.18.1,<0.22.0 by @dependabot in #227
• model_run_utils: return correct input_token_count by @dtrifiro in #228
• Add support for sequence lengths in eval by @alex-jw-brooks in #232
• Revert ":goal_net: Disallow empty train streams" by @gkumbhat in #234
• ⬆️ Update build requirement from <1.0,>=0.10.0 to >=0.10.0,<2.0 by @dependabot in #164
• Make verbalizer rendering optional in eval script by @alex-jw-brooks in #231
• 🧑‍💻 Fix docstring formatting function call by @gkumbhat in #219
• proposal: use setuptools/setuptools_scm for building by @dtrifiro in #216
• Update to tasks by @tharapalanivel in #236
• fix pylint warnings by @dtrifiro in #240
• pyproject: use setuptools' automatic discovery by @dtrifiro in #239
• 🚑🔧 Fix sequencing of arguments on run function by @gkumbhat in #241
• tox: run pytest with --durations flag to list tests run time by @dtrifiro in #246
• return correct finish reasons in generate_text_func by @dtrifiro in #210
• Speed up tests by @dtrifiro in #249
• 🐛 Fix loss tensor to float conversion by @gkumbhat in #258
• Add data limitation by @gkumbhat in #255
• fix uncaught exception in http client by @dtrifiro in #247
• Update training data validation to consider global and module level defaults by @gkumbhat in #264

New Contributors

• @jimknochelmann made their first contribution in #195
• @dtrifiro made their first contribution in #209

Full Changelog: 0.2.1...0.3.0

0.2.1

What's Changed

• Added benchmarking results to main README.md by @olson-ibm in #176
• Experiment sharding rebase (multi GPU support for Find Tuning) by @alex-jw-brooks and @gkumbhat in #156
• 🐛 Fix eval script for updated run datamodel by @gkumbhat in #184
• Add loss logging prompt-tuning by @gkumbhat in #189
• fix: use cli args for metrics to run by @timrbula in #193
• [caikit-nlp-163] Refactor peft module to take out common peft config functionality by @rawkintrevo and @alex-jw-brooks in #197
• SupportCaikitZeroTwenty: Bump caikit range to allow for 0.20 by @gabe-l-hart in #199
• Fix dtype prompt tuning by @gkumbhat in #198

New Contributors

• @timrbula made their first contribution in #193

Full Changelog: 0.2.0...0.2.1

0.2.0

What's Changed

• Lang modeling by @alex-jw-brooks in #95
• Fix logic for model type checking by @kellyaa in #30
• Fix local TGIS case for text-geneneration model loading by @Xaenalt in #114
• Add support causalm finetune by @gkumbhat in #80
• text generation local block by @Ssukriti in #79
• [NO-JIRA] Update README.md by @rawkintrevo in #110
• Consolidate tgis finetuning by @gkumbhat in #116
• Tgis auto finder by @gabe-l-hart in #123
• 🐛 Fix training arguments for service generation to work correctly by @gkumbhat in #122
• fixed simple typo in run_fine_tuning.py by @olson-ibm in #128
• Update fine-tuning example to allow local save of the model and flexible target seq len by @gkumbhat in #130
• ⬆️ Update caikit[runtime-grpc,runtime-http] requirement from <0.16.0,>=0.15.0 to >=0.15.0,<0.17.0 by @dependabot in #129
• Move to Caikit Interfaces by @tharapalanivel in #131
• Welcome back Gabe by @gkumbhat in #132
• Closes #134 by @olson-ibm in #135
• ⬆️ Update caikit[runtime-grpc,runtime-http] requirement from <0.17.0,>=0.16.0 to >=0.16.0,<0.18.0 by @dependabot in #142
• Fix stream api gen by @gkumbhat in #143
• 🔊 add value check logs by @joerunde in #148
• [CAIKIT-NLP-3] Remove device arg from .run by @rawkintrevo in #112
• 🩹📦 Fix peft installation by @gkumbhat in #149
• Update Accelerate dependency to fix import by @Maxusmusti in #147
• ✨ ExponentialDecayLengthPenalty data model by @tharapalanivel in #157
• Update README.md by @gkumbhat in #137
• Remove redacted git history by @alex-jw-brooks in #160
• Flattened inf params by @gkumbhat in #152
• ✨ Add support for additional generate params by @gkumbhat in #150
• Add more text generation inference params to TGIS modules by @tharapalanivel in #155
• eos_token bug fix by @tharapalanivel in #165
• 🐛 stop_sequences as list of str by @tharapalanivel in #168
• Fix seed type mismatch by @tharapalanivel in #171
• Update parameter selection doc by @gkumbhat in #172
• 🚚 Change parameter name and mark them optional for runtime by @gkumbhat in #173
• Unload prompts 180 by @gabe-l-hart in #183
• 🐛 Fix attention mask and task_id for MPT by @gkumbhat in #185
• Add Thara as maintainer 🥳 by @gkumbhat in #188

New Contributors

• @alex-jw-brooks made their first contribution in #95
• @kellyaa made their first contribution in #30
• @olson-ibm made their first contribution in #128
• @tharapalanivel made their first contribution in #131
• @joerunde made their first contribution in #148
• @Maxusmusti made their first contribution in #147

Full Changelog: 0.1.0...0.2.0

First release

What's Changed

• 👷 Use tox and run tests through Github workflows by @evaline-ju in #2
• ✏️ Fix model output types typo by @gkumbhat in #13
• 🚚 Rename package to caikit_nlp by @evaline-ju in #12
• Bump scikit-learn from 1.1.1 to 1.2.2 by @dependabot in #10
• Update caikit by @gkumbhat in #17
• Bump pandas from 1.4.2 to 2.0.2 by @dependabot in #6
• Bump tokenizers from 0.12.1 to 0.13.3 by @dependabot in #18
• Bump tqdm from 4.64.0 to 4.65.0 by @dependabot in #9
• ✨ Add text generation module by @gkumbhat in #16
• 🔊 Update log codes to NLP by @evaline-ju in #38
• Support tgis stop params by @gkumbhat in #50
• Update pyproject.toml accelerators version by @Xaenalt in #49
• ⬆️ Loosen dependency version ranges by @evaline-ju in #52
• 👷 Add publish to pypi by @evaline-ju in #53
• ✨ Text and token classification tasks and data models by @evaline-ju in #46
• ✨ Modules for filtered span classification enabling sentence content classification by @evaline-ju in #55
• Classification train record by @Ssukriti in #34
• ✨ Add streaming support for filtered span classification by @evaline-ju in #58
• 🐛 Fix streaming of chunked texts by @gkumbhat in #60
• 🐛 Fix issues with stream-span processing with trailing or leading whitespaces by @gkumbhat in #62
• Remove myself as a code owner by @gabe-l-hart in #64
• ⬆️ Bump caikit and caikit-tgis-backend by @evaline-ju in #67
• Add finetuning generation by @gkumbhat in #72
• ⬆️ Update caikit[runtime-grpc] requirement from <0.11.0,>=0.10.1 to >=0.10.1,<0.12.0 by @dependabot in #88
• ♻️ Use generated text result from caikit.interfaces by @evaline-ju in #91
• Api dumps by @gabe-l-hart in #93
• 🔧 Fix utils script to configure backends in the new way in updated caikit by @gkumbhat in #90
• Add eval fine tuning by @gkumbhat in #84
• 🐛 Fix autoconfig always fetching info from model-hub by @gkumbhat in #99
• Add output streaming text gen api by @gkumbhat in #96
• Remote tgis text gen by @gabe-l-hart in #107
• 🔥 Remove print in module code by @evaline-ju in #109
• Add Getting Started Notebook by @rawkintrevo in #106

New Contributors

• @evaline-ju made their first contribution in #2
• @gkumbhat made their first contribution in #13
• @dependabot made their first contribution in #10
• @Xaenalt made their first contribution in #49
• @Ssukriti made their first contribution in #34
• @gabe-l-hart made their first contribution in #64
• @rawkintrevo made their first contribution in #106

Full Changelog: https://github.com/caikit/caikit-nlp/commits/0.1.0