Transformer-lens

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 https://github.com/TransformerLensOrg/TransformerLens/pull/856
* Extend Bert support by degenfabian in https://github.com/TransformerLensOrg/TransformerLens/pull/829
* fixed bert indenting by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/875

New Contributors
* thisnick made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/856

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.14.1...v2.15.0

Reenables support for most recent version ofTransformerLens

What's Changed
* removed torch ceiling by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/865


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.14.0...v2.14.1

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

What's Changed
* moved setup python by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/855
* Refactor device selection by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/864


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.13.0...v2.14.0

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

What's Changed
* Upstream update by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/840
* Manually create repr for partial hooks by danbraunai in https://github.com/TransformerLensOrg/TransformerLens/pull/845
* updated artifacts version by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/850
* Upgrade transformers by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/849
* Ci hf token empty by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/853
* Add LLaVA support, modify generate function by zazamrykh in https://github.com/TransformerLensOrg/TransformerLens/pull/820
* Ci hf secret by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/854

New Contributors
* danbraunai made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/845
* zazamrykh made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/820

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.12.0...v2.13.0

What's Changed
* updated lock command by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/831
* Extend support for T5 models by degenfabian in https://github.com/TransformerLensOrg/TransformerLens/pull/832
* Added model Phi 4 by jonasrohw in https://github.com/TransformerLensOrg/TransformerLens/pull/833
* Phi 4 docs fix by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/839


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.11.0...v2.12.0

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 https://github.com/TransformerLensOrg/TransformerLens/pull/815
* Throw error when using attn_in with grouped query attention by degenfabian in https://github.com/TransformerLensOrg/TransformerLens/pull/810
* Feature llama 33 by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/826


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.10.0...v2.11.0