540 Release Candidate #14247
Open
540 Release Candidate #14247
+128,309
−76,104
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
Member
maziyarpanahi
commented
May 14, 2024
•
maziyarpanahi
commented
- Closed the S3 connection #14233
- openVINO Dependencies #14255
- [SPARKNLP-1037] Adding addFile changes to to replace broadcast in all ONNX based annotators #14236
- Integrating OpenVINO Runtime in Spark NLP #14200
- Fixing colab notebook bugs #14249
- adding model hub cards + updating readme + small typo fix on M2M100Te… #14253
- bert for zero shot classification crashes on sentence basis #14276
- Sparknlp 1035 test all notebooks to import tensor flow models to spark nlp #14238
- SPARKNLP-1036: Onnx Example notebooks #14234
- Adding caching to streamlit demos #14232
- Add openvino GPU dependency #14309
- LLAMA2 OpenVINO Position ID Fix #14308
- Sparknlp 1016 implement mp net for token classification #14322
- Uploading OpenVINO example notebooks #14313
- SparkNLP - 995 Introducing MistralAI LLMs #14318
- SparkNLP 1043 integrate new casual lm annotators to use open vino #14319
maziyarpanahi
added
enhancement
documentation
bug-fix
new-feature
… ONNX based annotators (#14236) * [SPARKNLP-1011] Adding changes to transfer ONNX files on executors through Spark files feature * [SPARKNLP-1011] Adding missing copyright comment * [SPARKNLP-1011] Adding changes to add prefix for models with onnx_data file * [SPARKNLP-1037] Adding changes to transfer ONNX files on executors via addFile * [SPARKNLP-1037] Adding unique suffix to avoid duplication in spark files
* Use OpenVINO model engine for BertEmbeddings Add OpenVINO model engine wrapper Add default buffer size for reading weights file Read OpenVINO IR format models * Use Long Tensors with XlmRoberta * Add OpenVINO support for RoBerta and XlmRoBerta embeddings * Fix data type and formatting * Add OpenVINO BERT test - Resole merge conflicts - Add test for openvino load model * Update Python APIs to use OpenVINO * Add param to enable OpenVINO through Python API * Formatting changes * Add OpenVINO support for E5 Embeddings * Enable OpenVINO backend for E5 Embeddings * Update Python APIs * Resolve merge issues * Add OpenVINO support for T5 * Read and write encoder-decoder models with OpenVINO * OpenVINO Async Inference * Refactor and cleanup * Update comments * Add config to set OpenVINO inference device * Add OpenVINO support for BERT Sentence Embeddings * Formatting * Openvino synchronous inference * Refactoring: OV Model Conversion * BertSentenceEmbeddings Python API * Enable OpenVINO support for Llama2 * Read/write Llama2 Transformer with OpenVINO * Bugfix: Update saved model filename * Replace broadcast with addFile for OpenVINO-based annotators * Add OpenVINO Wrapper tests * Add suffix to avoid duplication in Spark Files * Set default OV inference device to CPU * Use CPU by default for OpenVINO inference due to error loading device config in cluster envs * Bugfix: Read serialized model from folder
* adding code for spp files and updating notebooks * fixed code and notebook for xlnet embeddings * fixing more notebooks * adding notebook for bert sentence embeddings
…k nlp (#14238) * Updating file version in XlmRobertaForZeroShotClassification * updating transformer versions
* Delete examples/demos/streamlit/CLIPForZeroShotClassification/inputs directory * Add files via upload * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Update streamlit_app.py * Delete examples/demos/streamlit/run_demos.ipynb * Add files via upload
* implementing mpnet for tokenclassification * changing default pretrained model name --------- Co-authored-by: Maziyar Panahi <maziyar.panahi@iscpif.fr>
* added mistral * Mistral python API
…4319) * Phi2 scala api * Phi2 python api * Phi2 python and scala tests * Phi2 python and scala tests * added M2M100 openvino implementation * added phi2 openvino implementation * added openvino flag to python --------- Co-authored-by: Maziyar Panahi <maziyar.panahi@iscpif.fr>
* fixed LLAMA generation bug * update params
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.