-
Notifications
You must be signed in to change notification settings - Fork 659
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Bug Report]
convert_olmo3_weightszero-fills K/V weights whennum_key_value_heads == num_attention_headscomplexity-highVery complicated changes for people to address who are quite familiar with the codeVery complicated changes for people to address who are quite familiar with the codeHookedTransformerBug related to legacy HookedTransformer system. May not need to fix depending on severityBug related to legacy HookedTransformer system. May not need to fix depending on severityStatus: Open.#1620 In TransformerLensOrg/TransformerLens;[Bug Report]
convert_gpt_oss_weightsraisesTypeError: 'Tensor' object is not subscriptableon MXFP4 expertsbugSomething isn't workingSomething isn't workingcomplexity-highVery complicated changes for people to address who are quite familiar with the codeVery complicated changes for people to address who are quite familiar with the codeHookedTransformerBug related to legacy HookedTransformer system. May not need to fix depending on severityBug related to legacy HookedTransformer system. May not need to fix depending on severityStatus: Open.#1619 In TransformerLensOrg/TransformerLens;[Bug Report]
TransformerBridgeactivations on gpt-oss-20b disagree with the HF model it wrapsbugSomething isn't workingSomething isn't workingcomplexity-moderateModerately complicated issues for people who have intermediate experience with the codeModerately complicated issues for people who have intermediate experience with the codeTransformerBridgeBug specific to the new TransformerBridge systemBug specific to the new TransformerBridge systemStatus: Open.#1618 In TransformerLensOrg/TransformerLens;[Bug Report] generate() cannot be given an attention_mask, so pre-padded input silently produces wrong continuations
bugSomething isn't workingSomething isn't workingcomplexity-moderateModerately complicated issues for people who have intermediate experience with the codeModerately complicated issues for people who have intermediate experience with the codeTransformerBridgeBug specific to the new TransformerBridge systemBug specific to the new TransformerBridge systemStatus: Open.#1612 In TransformerLensOrg/TransformerLens;[Bug Report] TransformerBridge seq2seq loss ignores labels and derives decoder inputs/targets from encoder input_ids
bugSomething isn't workingSomething isn't workingcomplexity-moderateModerately complicated issues for people who have intermediate experience with the codeModerately complicated issues for people who have intermediate experience with the codeTransformerBridgeBug specific to the new TransformerBridge systemBug specific to the new TransformerBridge systemStatus: Open.#1611 In TransformerLensOrg/TransformerLens;[Bug Report] Native init drifts from
HookedTransformer: unresolvedinitializer_rangesentinel and ignored xavier/kaiming gaincomplexity-moderateModerately complicated issues for people who have intermediate experience with the codeModerately complicated issues for people who have intermediate experience with the codegood first issueGood for newcomersGood for newcomershelp wantedExtra attention is neededExtra attention is neededTransformerBridgeBug specific to the new TransformerBridge systemBug specific to the new TransformerBridge systemStatus: Open.[Proposal] Jacobian Lens follow-up: validation deliverables + deferred PR2 scope
complexity-moderateModerately complicated issues for people who have intermediate experience with the codeModerately complicated issues for people who have intermediate experience with the codegood first issueGood for newcomersGood for newcomershelp wantedExtra attention is neededExtra attention is neededtoolingAnything pertaining to outside tools used within the codebaseAnything pertaining to outside tools used within the codebaseTransformerBridgeBug specific to the new TransformerBridge systemBug specific to the new TransformerBridge systemStatus: Open.[Bug Report] [macOS-arm64] Cached eager attention NaNs in transformers v5 — blocks bridge KV-cache generation
discussionNo action needed yetNo action needed yetseen_by_maintainersConfirms that a maintainer is aware of this card.Confirms that a maintainer is aware of this card.toolingAnything pertaining to outside tools used within the codebaseAnything pertaining to outside tools used within the codebasewontfixThis will not be worked onThis will not be worked onStatus: Open.#1322 In TransformerLensOrg/TransformerLens;[Proposal] Add support for
cpu,meta, anddiskto TransformerBridgedevice_mapcomplexity-moderateModerately complicated issues for people who have intermediate experience with the codeModerately complicated issues for people who have intermediate experience with the codeenhancementNew feature or requestNew feature or requesthelp wantedExtra attention is neededExtra attention is neededTransformerBridgeBug specific to the new TransformerBridge systemBug specific to the new TransformerBridge systemStatus: Open.#1280 In TransformerLensOrg/TransformerLens;[Question] How do I add a custom generative video transformer into TransformerLens?
complexity-highVery complicated changes for people to address who are quite familiar with the codeVery complicated changes for people to address who are quite familiar with the codeStatus: Open.#869 In TransformerLensOrg/TransformerLens;[Proposal] Add support for TracrBench
complexity-highVery complicated changes for people to address who are quite familiar with the codeVery complicated changes for people to address who are quite familiar with the codenew-architectureThis card involves adding a new architecture .This card involves adding a new architecture .Status: Open.#704 In TransformerLensOrg/TransformerLens;[Bug Report] Demo for Tracr to TransformerLens is kind of broken
bugSomething isn't workingSomething isn't workingdemoCreating a demo or tutorialCreating a demo or tutorialStatus: Open.#481 In TransformerLensOrg/TransformerLens;