Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture #12466
+169
−39
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
- Adds MoE-based embedding model supporting multilingual embeddings. - Selects architecture variant based on hyperparameter detection (MoE layers). - Removes unnecessary subclass initialization checks for clarity. https://www.nomic.ai/blog/posts/nomic-embed-text-v2 Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Adam Treat <treat.adam@gmail.com>
ngxson
reviewed
Mar 19, 2025
| @@ -702,6 +695,8 @@ def get_vocab_base_pre(self, tokenizer) -> str: | |||
| if chkhsh == "ccc2ef013c104be7bae2965776d611e1d7a8a2a9c547dd93a682c9a9fc80352e": | |||
| # ref: https://huggingface.co/Xenova/gpt-4o | |||
| res = "gpt-4o" | |||
| if chkhsh == "a81863d07e75497e2194eb1a1574d5e5cd4d5f85a87a0728b922bf2bed6fb327": | |||
| res = "bert" | |||
There was a problem hiding this comment.
The newly added tokenizer is nomic-embed-text-v2-moe and not bert, is this expected?
And also this list is auto-generated, please make sure not to modify it manually
ngxson
reviewed
Mar 19, 2025
|
|
||
| if "mlp.experts.mlp.w1" in name: | ||
| data_torch = data_torch.view(self.hparams["num_experts"], self.hparams["n_inner"], self.hparams["n_embd"]) | ||
| return [(self.map_tensor_name(name) + ".weight", data_torch)] |
There was a problem hiding this comment.
will this work? (no need to return here)
map_tensor_name will append .weight if the given original name also have it
Suggested change
| return [(self.map_tensor_name(name) + ".weight", data_torch)] | |
| name += ".weight" |
ngxson
reviewed
Mar 19, 2025
|
Working on tests to verify the accuracy of the model |
Signed-off-by: Adam Treat <treat.adam@gmail.com>
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.
https://www.nomic.ai/blog/posts/nomic-embed-text-v2
Make sure to read the contributing guidelines before submitting a PR