v2.15.4

What's Changed

• passed secret explicitly by @bryce13950 in #927

Full Changelog: v2.15.3...v2.15.4

v2.15.3

What's Changed

• updated triggers to enforce secrets by @bryce13950 in #926

Full Changelog: v2.15.2...v2.15.3

v2.15.2

What's Changed

• fixed wrapping by @bryce13950 in #925

Full Changelog: v2.15.1...v2.15.2

v2.15.1

Minor fix to LLaMA rope compatibility and a fix for the CI

What's Changed

• added full hf token authentication by @bryce13950 in #916
• Fix LLama RoPE by @mntss in #910

Full Changelog: v2.15.0...v2.15.1

v2.15.0

Nice little update! This one improves compatibility for LLaMA 3.3 70B, adds a new mistral mode, and introduces a number of utilities for Bert.

What's Changed

• Fixes compatibility with Llama 3.3 70B by @thisnick in #856
• Extend Bert support by @degenfabian in #829
• fixed bert indenting by @bryce13950 in #875

New Contributors

• @thisnick made their first contribution in #856

Full Changelog: v2.14.1...v2.15.0

v2.14.1

Reenables support for most recent version ofTransformerLens

What's Changed

• removed torch ceiling by @bryce13950 in #865

Full Changelog: v2.14.0...v2.14.1

v2.14.0

Much more robust, but still experimental multi-GPU support!

What's Changed

• moved setup python by @bryce13950 in #855
• Refactor device selection by @bryce13950 in #864

Full Changelog: v2.13.0...v2.14.0

v2.13.0

Nice little maintenance one, and a large expansion of generation to allow support for vision models!

What's Changed

• Upstream update by @bryce13950 in #840
• Manually create repr for partial hooks by @danbraunai in #845
• updated artifacts version by @bryce13950 in #850
• Upgrade transformers by @bryce13950 in #849
• Ci hf token empty by @bryce13950 in #853
• Add LLaVA support, modify generate function by @zazamrykh in #820
• Ci hf secret by @bryce13950 in #854

New Contributors

• @danbraunai made their first contribution in #845
• @zazamrykh made their first contribution in #820

Full Changelog: v2.12.0...v2.13.0

v2.12.0

What's Changed

• updated lock command by @bryce13950 in #831
• Extend support for T5 models by @degenfabian in #832
• Added model Phi 4 by @jonasrohw in #833
• Phi 4 docs fix by @bryce13950 in #839

Full Changelog: v2.11.0...v2.12.0

v2.11.0

LLaMA 3.3 support! This release also includes a handful of usability improvements.

What's Changed

• Set prepend_bos to false by default for Qwen models by @degenfabian in #815
• Throw error when using attn_in with grouped query attention by @degenfabian in #810
• Feature llama 33 by @bryce13950 in #826

Full Changelog: v2.10.0...v2.11.0