├── .gitignore ├── LICENSE ├── README.md ├── imgs └── chunk-text.png ├── notebooks ├── agent-system-langgraph-vllm-elasticsearch-qwen.ipynb ├── dataset-collator.ipynb ├── tokenizer-three-approaches-with-chat-template.ipynb └── tokenizer-three-approaches.ipynb └── src ├── .gitkeep └── preprocess └── basic.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/README.md -------------------------------------------------------------------------------- /imgs/chunk-text.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/imgs/chunk-text.png -------------------------------------------------------------------------------- /notebooks/agent-system-langgraph-vllm-elasticsearch-qwen.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/notebooks/agent-system-langgraph-vllm-elasticsearch-qwen.ipynb -------------------------------------------------------------------------------- /notebooks/dataset-collator.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/notebooks/dataset-collator.ipynb -------------------------------------------------------------------------------- /notebooks/tokenizer-three-approaches-with-chat-template.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/notebooks/tokenizer-three-approaches-with-chat-template.ipynb -------------------------------------------------------------------------------- /notebooks/tokenizer-three-approaches.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/notebooks/tokenizer-three-approaches.ipynb -------------------------------------------------------------------------------- /src/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/preprocess/basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mddunlap924/NLP-Essentials-with-Hugging-Face/main/src/preprocess/basic.py --------------------------------------------------------------------------------