unilm
csv-import
| unilm | csv-import | |
|---|---|---|
| 41 | 17 | |
| 18,614 | 1,601 | |
| 3.0% | 1.9% | |
| 9.0 | 9.8 | |
| 3 days ago | about 2 months ago | |
| Python | TypeScript | |
| MIT License | 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.
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
csv-import
- Show HN: We built a developer-first open-source CSV import platform
- Inquery: Open-Source Safe Data Changes for PostgreSQL
- Inquery: An open-source tool for making safe SQL updates
- Show HN: Safe Data Changes in PostgreSQL
-
I got a data engineering horror story, what is yours?
I'm actually working on an open-source tool for making production data updates safer (think GitHub-like review for changes + safeguards with change preview, query plan, etc.)
- FLiPN-FLaNK Stack for March 6, 2023
- Show HN: Inquery (YC W23) – Real-time events for Postgres
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
spotless - Keep your code spotless
ERNIE - Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
memphis-cli-old - Memphis is an event processing platform
involution - [CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
loghook - ⚡ logger to notify logs to slack,discord using webhook ⚡
gensim - Topic Modelling for Humans
qr-code - A no-framework, no-dependencies, customizable, animate-able, SVG-based <qr-code> HTML element.
maelstrom - A workbench for writing toy implementations of distributed systems.
quix-streams - A Python library for building containerized ML and Generative AI applications with Apache Kafka.
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