Merged
Conversation
Closed
martindevans
force-pushed
the
llama_embedder_2
branch
from
f8445df to
c06fb81
Compare
Member
Author
|
Rebased onto #905 |
…anov/llama.cpp/tree/master/examples/embedding. New embedder properly handles pooling, either returning one embedding for the whole sequence or one per token. - Added `Encode` methods to `LLamaContext` - Moved some native methods from `NativeApi` to `SafeLLamaContextHandle` and wrapped them properly - Added `HasDecoder` property to `SafeLlamaModelHandle`. This function doesn't exist in the current version of llama.cpp, will need to be hooked up in the next binary update - Added some normalization methods as extensions on span/array. This required adding a dependency on `System.Numerics.Tensors`
- Using `llama_set_embeddings` to toggle on embedding mode, so it no longer needs to be specified in the params
martindevans
force-pushed
the
llama_embedder_2
branch
from
c06fb81 to
a3028de
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Totally rewritten the LLamaEmbedder based on https://github.com/ggerganov/llama.cpp/tree/master/examples/embedding. New embedder properly handles pooling, either returning one embedding for the whole sequence or one per token. This rewrite does not support batching, it's still just one string at a time.
Encodemethods toLLamaContextNativeApitoSafeLLamaContextHandleand wrapped them properlyHasDecoderproperty toSafeLlamaModelHandle. This function doesn't exist in the current version of llama.cpp, will need to be hooked up in the next binary updateSystem.Numerics.TensorsDRAFT until the
HasDecoderfunction exists, after the next binary update.