rag e2e first commit #2
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
shamanez
commented
Aug 31, 2023
| from transformers import AutoModel | ||
|
|
||
|
|
||
| class AutoModelForSentenceEmbedding(torch.nn.Module): |
There was a problem hiding this comment.
I would add the causal language model to this class. Obviously we can change the class name.
Reason: In future, if we are to use accelerate with deep speed, it won't work with two models for now.
| self.normalize = normalize | ||
| self.tokenizer = tokenizer | ||
|
|
||
| def forward(self, **kwargs): |
There was a problem hiding this comment.
If you add a casual language model to the above init function. You can easily add another parameter for the forward position and get the output from either the retriever or the generator.
like model_type
|
|
||
| if is_diffusers_available(): | ||
| from .models import ( | ||
| DDPOPipelineOutput, |
There was a problem hiding this comment.
I can change these naming later, so don't worry.
| logprobs_logits, doc_logprobs, query_token_length | ||
| ) | ||
|
|
||
| loss = get_nll(marginalized_log_probs, input_tensors[:, 1:]) |
There was a problem hiding this comment.
let's get the mean loss here.
batch_size * 1
|
|
||
| # Prepare everything with our `accelerator`. | ||
| # see https://github.com/huggingface/accelerate/issues/253#issuecomment-1253231210 | ||
| r_model, c_model = accelerator.prepare(r_model, c_model) |
shamanez
commented
Aug 31, 2023
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Outdated suggestions cannot be applied.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.
No description provided.