scratch-pdf-bot
unilm
scratch-pdf-bot | unilm | |
---|---|---|
2 | 41 | |
36 | 18,548 | |
- | 2.7% | |
6.0 | 9.0 | |
7 months ago | 3 days ago | |
Python | Python | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
scratch-pdf-bot
-
Show HN: Lance is a Rust-based alternative to Parquet for ML data
I initially built this same "chat with PDFs" prototype with LangChain and qdrant. I then rebuilt it from scratch for the sake of learning and comparison.
Some context: I've been a jack-of-all-trades data scientist / machine learning engineer for the past 15 years (officially titled as an MLE the last four years).
I share that only because I think it plays a role in how I'm typically accustomed to working.
1. I found LangChain to be overkill for this use-case. While it might allow some to move more quickly when building, I found it to be cumbersome. My suspicion is this is largely because of my background - I understand how to build much of what's "under the hood" in LangChain. Because of this, I think it felt overly abstracted and I found the docs difficult to navigate and sometimes incomplete.
2. I used Qdrant via their docker image and it was simple to setup and start using. I didn't try to push the limits with it, so I can't say anything about performance. Because Qdrant runs as an http service, I found that it didn't fit well into my workflow - I'm accustomed to being able to visually inspect my data inside the interpreter, debugging, trying out commands, interacting and experimenting with my results, etc. Again, my suspicion is this is my own bias in how I typically work. Qdrant otherwise seemed very nice.
3. LanceDB felt powerful yet lightweight, and fit well into my workflow. It was far more intuitive for me. It was as if sqlite, the python data ecosystem, and a vector database had a child and named it LanceDB. Under the hood, it's built on Apache Arrow and integrates nicely with pandas, allowing me to seamlessly go from LanceDB table on disk, to pandas dataframe, and into some analysis or investigation of my LanceDB query results. This line [1] is a great example of why I liked it. This feels nicer to me than the world of API params and HTTP requests.
1. https://github.com/gjreda/scratch-pdf-bot/blob/main/gpt_pdf_...
unilm
- The Era of 1-Bit LLMs: Training_Tips, Code And_FAQ [pdf]
- The Era of 1-Bit LLMs: Training Tips, Code and FAQ
-
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
+1 On this, the real proof would have been testing both models side-by-side.
It seems that it may be published on GitHub [1] according to HuggingFace [2].
[1] https://github.com/microsoft/unilm/tree/master/bitnet
[2] https://huggingface.co/papers/2402.17764
- I'm an Old Fart and AI Makes Me Sad
-
On building a semantic search engine
e5-mistral is essentially a distillation from gpt-4 to a smaller model. You can see here https://github.com/microsoft/unilm/blob/16da2f193b9c1dab0a69...
they actually have custom prompts for each dataset being tested.
Question would be, if you haven't seen the task before, what is a good prompt to prepend for your task?
IMO e5-mistral is overfit to MTEB
-
Leveraging GPT-4 for PDF Data Extraction: A Comprehensive Guide
Layout LM v1, v2 and v3 models [ Github ] DocBERT [ Github ]
-
Microsoft Publishes LongNet: Scaling Transformers to 1,000,000,000 Tokens
The repository is available here.
-
Recommended open LLMs with image input modality?
It is missing kosmos-2. I remember its image captioning was(demo currently down) really good and it's almost as fast as llava and lavin.
-
LongNet: Scaling Transformers to 1,000,000,000 Tokens
Should be this: https://github.com/microsoft/unilm/
-
[R] LongNet: Scaling Transformers to 1,000,000,000 Tokens
This is from Microsoft Research (Asia). https://aka.ms/GeneralAI
What are some alternatives?
lance - Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, with more integrations coming..
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
chatgpt-comparison-detection - Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥
ERNIE - Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
RasaGPT - 💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram
involution - [CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
embedditor - ⚡ GUI for editing LLM vector embeddings. No more blind chunking. Upload content in any file extension, join and split chunks, edit metadata and embedding tokens + remove stop-words and punctuation with one click, add images, and download in .veml to share it with your team.
gensim - Topic Modelling for Humans
sycamore - 🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
maelstrom - A workbench for writing toy implementations of distributed systems.
deeplake - Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai
rasa - 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants