[Ernie 4.5] Add ernie text models
#39228
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
… focussing on modeling other models first)
|
run-slow: ernie4_5 |
|
This comment contains run-slow, running the specified jobs: models: ['models/ernie4_5'] |
|
Let's go! 🚀 |
…r modular and transformers style rope (complex view)
ArthurZucker
approved these changes
Jul 21, 2025
Comment on lines
+2980
to
+2989
| # Passing hooks over to the embeddings if needed | ||
| # (currently limited to tensor parallel hooks and flags only) | ||
| if hasattr(input_embeddings, "_is_hooked") and getattr(input_embeddings, "_hf_tp_plan", None): | ||
| output_embeddings._is_hooked = input_embeddings._is_hooked | ||
| output_embeddings._hf_tp_plan = input_embeddings._hf_tp_plan | ||
| output_embeddings._forward_hooks = input_embeddings._forward_hooks | ||
| output_embeddings._forward_pre_hooks = input_embeddings._forward_pre_hooks | ||
| output_embeddings.__repr__ = ( | ||
| lambda: f"{output_embeddings.__repr__()}\nTP Plan: {output_embeddings._hf_tp_plan}" | ||
| ) |
|
[For maintainers] Suggested jobs to run (before merge) run-slow: auto, ernie4_5, ernie4_5_moe |
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
Jul 22, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
zaristei
pushed a commit
to zaristei/transformers
that referenced
this pull request
Sep 9, 2025
* init * copied from remote * add proper structure and llama like structure * fixup * revert to state that works * get closer to llama * slow and steady * some removal * masks work * it is indeed the rope implementation, how dafuq does it mesh with the cache now hmm * nice * getting closer * closer to transformers style * let's simplify this, batching works now * simplified * working version with modular * it is indeed the rotation per weights, make it complete llama style * cleanup conversion, next to look at -> tokenizer * remove llama artefacts * fix modeling tests (common ones) * style * integration test + first look into tokenization (will need more work, focussing on modeling other models first) * style * working moe version, based on remote * lets keep it simple and go step by step - transformers annotations for modular and transformers style rope (complex view) * more cleanup * refactor namings and remove addition forXXX classes * our moe won't cut it it seems, correction bias seems to be missing in remote code version * tokenization change (remote) * our moe version works when adding normalization :D * cleanup moe * nits * cleanup modeling -> let's get to modular next * style * modular v1 * minor things + attempt at conversion (which doesn't work) * no conversion follow glm, fixup modular and other nits * modular cleanup * fixes * tests, tests, tests + some moe dtype forcing * simplify modular, fix fatal fa2 bug, remaining tests * fix import issue? * some initial docs, fix bnb faulty behavior --> needs to fix some tests because of gate needing to be float * fix sdpa test, load on init dtype only * fixup post merge * style * fix doc links * tokenization cleanup beginnings * simplify tokenizer by a lot as its basically llama * tokenizer is full llama with different defaults + extra special tokens * sync og special tokens of ernie * fix decoding with numbers (also in remote done what a timing), begin of tok tests * align with remote and preserve special tokens, adjust tests to ernie legacy behavior, warning for questionable behavior (also in llama) * nits * docs * my daily post merge it is * check * tokenization update with explanations and conversion script * review on modular (til), revert some tokenizer things i did prior, remove mtp comment (low prio) * post merge fixes * fixup tokenization, llama fast is the way to go * more fixups * check * import fixes * correction bias following the paddle code * fix * fix TP plan, fix correction bias sharding during forward * style * whoops * fix tied weights * docs and last nit * license * flasky tests * move repo id, update when merged on the hub
5 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adding the Ernie 4.5 suite of models.
Progress:
Conversionseeconvert...tokenizerNew/Followup PR: