0.0.5

CLI support for evals!

What's Changed

• updated readme by @danielhstahl in #53
• Llama index finetune arcee data by @Ben-Epstein in #54
• refactor eval code, create eval cli by @Ben-Epstein in #55

New Contributors

• @danielhstahl made their first contribution in #53

Full Changelog: 0.0.4...0.0.5

0.0.4

What's Changed

• align names to rage2e params by @Ben-Epstein in #52

Full Changelog: 0.0.3...0.0.4

0.0.3

What's Changed

• move exp into folder by @Ben-Epstein in #48
• Fix dataset load by @Ben-Epstein in #49

Full Changelog: 0.0.2...0.0.3

0.0.2

What's Changed

• docs and fix loading data in retriever only by @Ben-Epstein in #44
• Chore/training experiment by @Ben-Epstein in #47

Full Changelog: 0.0.1...0.0.2

0.0.1

Open Source DALM 🚀

What's Changed

• Casual rag by @shamanez in #1
• rag e2e first commit by @shamanez in #2
• Remove hardcoded dataset by @SachiraKuruppu in #5
• revisisted the LLM loss function by @shamanez in #6
• Add static methods for bnb and lora configs by @SachiraKuruppu in #7
• added initial evals by @shamanez in #8
• Refactor rag e2e evaluation by @SachiraKuruppu in #9
• [1] repo setup: tests, linting, ci, typing by @Ben-Epstein in #10
• [2] eval and datasets dirs setup by @Ben-Epstein in #13
• Refactor the codebase by @SachiraKuruppu in #14
• Fix accelerator issue by @SachiraKuruppu in #16
• added the peft layey attachment by @shamanez in #18
• Fix formatting issue by @SachiraKuruppu in #19
• Add the question answer generation script by @SachiraKuruppu in #20
• Distribute typing by @Ben-Epstein in #24
• Fix retriever only training by @SachiraKuruppu in #25
• Take max length as CLI parameters by @SachiraKuruppu in #27
• Updated the current README. by @shamanez in #28
• Add login to eval script. Fix minor problems by @SachiraKuruppu in #29
• revisited the README and max token lengths by @shamanez in #30
• Max token lengths args by @shamanez in #31
• Update eval_with_hnsw.py by @shamanez in #35
• License and Example DALMs by @Jacobsolawetz in #39
• Chore/opti eval by @Ben-Epstein in #38
• Modified the evaluation scripts for the clarity by @shamanez in #37
• [WIP] Add evaluation results to README by @metric-space in #40
• Update README.md by @mmcquade11 in #41
• split dataset by title by @Ben-Epstein in #42
• Add lora dropout and remove non-required input param by @metric-space in #43
• OSS work: sdk and cli support for training retriever, e2e, and qa-gen, license by @Ben-Epstein in #33

New Contributors

• @shamanez made their first contribution in #1
• @SachiraKuruppu made their first contribution in #5
• @Ben-Epstein made their first contribution in #10
• @Jacobsolawetz made their first contribution in #39
• @metric-space made their first contribution in #40
• @mmcquade11 made their first contribution in #41

Full Changelog: https://github.com/arcee-ai/DALM/commits/0.0.1