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

v2.10.0

Huge update! This is likely going to be the last big 2.x update. This update greatly improves model implementation accuracy, and adds some of the newer Qwen models.

What's Changed

• Remove einsum in forward pass in AbstractAttention by @degenfabian in #783
• Colab compatibility bug fixes by @degenfabian in #794
• Remove einsum usage from create_alibi_bias function by @degenfabian in #781
• Actions token access by @bryce13950 in #797
• Remove einsum in apply_causal_mask in abstract_attention.py by @degenfabian in #782
• clarified arguments a bit for hook_points by @bryce13950 in #799
• Remove einsum in logit_attrs in ActivationCache by @degenfabian in #788
• Remove einsum in compute_head_results in ActivationCache by @degenfabian in #789
• Remove einsum usage in refactor_factored_attn_matrices in HookedTransformer by @degenfabian in #791
• Remove einsum usage in _get_w_in_matrix in SVDInterpreter by @degenfabian in #792
• Remove einsum usage in forward function of BertMLMHead by @degenfabian in #793
• Set default_prepend_bos to False in Bloom model configuration by @degenfabian in #806
• Remove einsum in complex_attn_linear by @degenfabian in #790
• Add a demo of collecting activations from a single location in the model. by @adamkarvonen in #807
• Add support for Qwen_with_Questions by @degenfabian in #811
• Added support for Qwen2.5 by @israel-adewuyi in #809
• Updated devcontainers to use python3.11 by @jonasrohw in #812

New Contributors

• @israel-adewuyi made their first contribution in #809
• @jonasrohw made their first contribution in #812

Full Changelog: v2.9.1...v2.10.0

v2.9.1

Minor dependency change to address a change in an outside dependency

What's Changed

• added typeguard dependency by @bryce13950 in #786

Full Changelog: v2.9.0...v2.9.1

v2.9.0

Lot's of accuracy improvements! A number of models are behaving closer to how they behave in Transformers, and a new internal configuration has been added to allow for more ease of use!

What's Changed

• fix the bug that attention_mask and past_kv_cache cannot work together by @yzhhr in #772
• Set prepend_bos to false by default for Bloom model family by @degenfabian in #775
• Fix that if use_past_kv_cache is set to True models from the Bloom family produce weird outputs. by @degenfabian in #777

New Contributors

• @yzhhr made their first contribution in #772
• @degenfabian made their first contribution in #775

Full Changelog: v2.8.1...v2.9.0

v2.8.1

New notebook for comparing models, and bug fix with dealing with newer LLaMA models!

What's Changed

• Logit comparator tool by @curt-tigges in #765
• Add support for NTK-by-Part Rotary Embedding & set correct rotary base for Llama-3.1 series by @Hzfinfdu in #764

New Contributors

• @Hzfinfdu made their first contribution in #764

Full Changelog: v2.8.0...v2.8.1