Hi, I'm amachine learning engineer focusing/focused on:NLP,recommender system,quantitative finance.

I havemachine learning,backend engineering anddata engineering experiences, following are thetech stacks I used before:

• Programming Languages:Python, C++, Java (Only for Data-Engineering), SQL, JavaScript, Shell, Rust (A Little)
• Frameworks, Libs or Tools:Pulsar, Milvus, gRPC, Spark, Hive, K8S, PyTorch, FAISS, Redis, Flask, TensorFlow (Long Time Ago)

Here is myprojects index:

• Side Projects

  • simpler-distil-whisper:Reproduce paperDistil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling.
  • PLM-ICD-multi-label-classifier:Reproduce paperPLM-ICD: Automatic ICD Coding with Pretrained Language Models.
  • SlimPajama-DC Data Deduplicator:Reproduce paperSlimPajama-DC: Understanding Data Combinations for LLM Training.
  • feather: AC++feature-hash lib withPython binding provided.
  • osimhash: APython binder oversimhashC++ text deduplication lib.
  • pypack: GeneratesPython runtime tar.gz file (forPySpark) runnable on all python-version/os/platforms.

• Codes Reading

  • fastTextAnnotation: The very detailed code annotation for facebook fasttext lib.
  • hnswlibAnnotation: The very detailed code annotation for hnswlib.
  • finBERT: BERT for financial news sentiment classification.

• Self Using

  • quicmd: Some useful quickly execution commands.
  • config4: Some self-using configs, for now about tmux and vim.
  • wiki4codes: Some lib/framework/algorithms/models' trials recording, demos, examples, etc...

Popular repositoriesLoading

1. PLM-ICD-multi-label-classifierPLM-ICD-multi-label-classifierPublic

   A multi-label classifier based on PLM-ICD paper

   Python 6

2. featherfeatherPublic

   FEATure HashER

   C++ 3 2

3. osimhashosimhashPublic

   A deduplication lib built Over [SIMHASH](https://github.com/yanyiwu/simhash).

   C++ 2

4. simpler-distil-whispersimpler-distil-whisperPublic

   Simpler Distil-Whisper

   Python 2

5. pypackpypackPublic

   makes PYthon environment PACKageable.

   Python 1

6. imagesimagesPublic

   images to link markdown