add mlp bias for llama models #30031
Merged
Conversation
This file contains 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
|
@younesbelkada light ping again |
ArthurZucker
reviewed
Apr 5, 2024
There was a problem hiding this comment.
Hey! Though this is not necessarily against our transformers philosophy, we would need to have justification: meaning a new cool model released rather than a promise that it will be release!
This should be easy to have on the hub with trust_remote_code=True no?
ArthurZucker
approved these changes
May 3, 2024
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
Thanks everyone for the quick turnaround 🤗 |
This was referenced May 6, 2024
njhill
pushed a commit
to IBM/text-generation-inference
that referenced
this pull request
May 6, 2024
#### Motivation The `Calico` models currently set the mlp and attention bias to true, which was hard-coded to false in flash and paged llama implementations. This will use the config params set in huggingface/transformers#30031 to set those values properly. #### Modifications - added attention_bias, mlp_bias to config for Flash and Paged Llama implementations (default is False) - set bias in attention and mlp to the config value #### Result Models should be able to load properly if containing attention and mlp bias --------- Signed-off-by: Joshua Rosenkranz <[email protected]> Signed-off-by: Joe Runde <[email protected]> Co-authored-by: Joe Runde <[email protected]>
heyselbi
pushed a commit
to heyselbi/text-generation-inference
that referenced
this pull request
May 7, 2024
…atahub-io#85) #### Motivation The `Calico` models currently set the mlp and attention bias to true, which was hard-coded to false in flash and paged llama implementations. This will use the config params set in huggingface/transformers#30031 to set those values properly. #### Modifications - added attention_bias, mlp_bias to config for Flash and Paged Llama implementations (default is False) - set bias in attention and mlp to the config value #### Result Models should be able to load properly if containing attention and mlp bias --------- Signed-off-by: Joshua Rosenkranz <[email protected]> Signed-off-by: Joe Runde <[email protected]> Co-authored-by: Joe Runde <[email protected]>
Xaenalt
pushed a commit
to Xaenalt/text-generation-inference
that referenced
this pull request
Aug 7, 2024
#### Motivation The `Calico` models currently set the mlp and attention bias to true, which was hard-coded to false in flash and paged llama implementations. This will use the config params set in huggingface/transformers#30031 to set those values properly. #### Modifications - added attention_bias, mlp_bias to config for Flash and Paged Llama implementations (default is False) - set bias in attention and mlp to the config value #### Result Models should be able to load properly if containing attention and mlp bias --------- Signed-off-by: Joshua Rosenkranz <[email protected]> Signed-off-by: Joe Runde <[email protected]> Co-authored-by: Joe Runde <[email protected]>
Xaenalt
pushed a commit
to Xaenalt/text-generation-inference
that referenced
this pull request
Aug 12, 2024
#### Motivation The `Calico` models currently set the mlp and attention bias to true, which was hard-coded to false in flash and paged llama implementations. This will use the config params set in huggingface/transformers#30031 to set those values properly. #### Modifications - added attention_bias, mlp_bias to config for Flash and Paged Llama implementations (default is False) - set bias in attention and mlp to the config value #### Result Models should be able to load properly if containing attention and mlp bias --------- Signed-off-by: Joshua Rosenkranz <[email protected]> Signed-off-by: Joe Runde <[email protected]> Co-authored-by: Joe Runde <[email protected]>
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.
This adds bias support for MLP in Llama
Can we add this?
It would help a lot for some models we are developing
@ArthurZucker and @younesbelkada
This lets us re-use the llama model class for our models :) without adding another class for a new model.