detectivelyw @detectivelyw

Computer scientist & Anime lover Chandler, AZ Joined August 2014

Tweets

2K
Followers

159
Following

2K
Likes

6K

Haihao Shen @HaihaoShen

6 months ago

💡INC v3.3 released with enhanced FP8 and INT4 quantization performance on Intel platforms. Validated on most recent LLMs e.g., DeepSeekV3/R1, Falcon, Phi etc. github.com/intel/neural-c…🌟

0 18 84 3K 13

Just put together a short Jupyter notebook with tips and tricks for reducing memory usage when loading larger and larger models (like LLMs) in PyTorch: github.com/rasbt/LLMs-fro… (PS: This is an LLM example but the same concepts apply to any PyTorch model)

18 418 3K 157K 3K

Download Image

Rohan Paul @rohanpaul_ai

12 months ago

A cool Github repo collecting LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

16 396 3K 198K 3K

Download Image

Ethan Mollick @emollick

a year ago

Wow: Just tried PaperQA, an open source AI-powered literature review whose research paper claims it achieves "superhuman synthesis of scientific knowledge" I tested it against papers I wrote and it seems like the real deal, putting together a good summary with accurate details.

25 243 2K 178K 2K

Download Image

elvis @omarsar0

a year ago

RAG vs. Long-Context LLMs I have yet to see a convincing paper or technical blog showing that long-context LLMs can or will replace RAG. So far I've seen specific long-context applications where long-context LLMs thrive and current retrieval benchmarks are not convincing. This…

19 226 1K 158K 847

Download Image

Rohan Paul @rohanpaul_ai

a year ago

Evaluating your LLM applications with the right metrics is super important for production-class applications. Roughly we have two types of evaluations 1. LLM model itself is evaluated across different tasks on its conciseness, relevance, coherence, faithfulness, etc. 2. RAG…

7 51 244 20K 236

Download Image

Rohan Paul @rohanpaul_ai

a year ago

MASSIVE work by IBM Research. AutoToS: Automated version of Thought of Search 👏 Achieved 100% accuracy across all evaluated domains 🤯 AutoToS generates sound, complete search components from LLMs without human feedback, achieving high accuracy across domains. Original Problem…

7 123 588 44K 628

Download Image

Henry Ndubuaku @Henry_Ndubuaku

a year ago

One of my mentees just completed his second project with me: SciKit-Jax: github.com/LiibanMo/sciki… Scikit-Learn does not leverage GPUs by itself and offers less flexibility in the model design. Scikit-Jax solves these! He will polish this to accommodate multi-GPU setups once we…

8 20 138 14K 68

Sumit @_reachsumit

a year ago

HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction Combines VectorRAG and GraphRAG techniques to improve information extraction from financial documents. 📝arxiv.org/abs/2408.04948

1 38 159 9K 102

Download Image

elvis @omarsar0

a year ago

Combining GraphRAG and VectorRAG leads to a HybridRAG system that outperforms both individually. It was tested on a set of financial earning call transcripts. Combining the advantages of both approaches provides more accurate answers to queries. arxiv.org/abs/2408.04948

15 139 602 51K 571

Download Image

Ningyu Zhang@ZJU @zxlzr

a year ago

We will present EasyEdit tomorrow at #ACL24 @aclmeeting. Location: Mon 11:00-12:30@Convention Center A1, Poster Session A EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (Demo) Can't wait to connect and chat with everyone there! 🌟 #ACL2024…

1 10 55 4K 19

Download Image

elvis @omarsar0

a year ago

Nice survey paper on current practices and solutions for LLM-based agents for software engineering. Covers important topics such as requirement engineering, code generation, test generation, and autonomous decision making. It also includes benchmarks, metrics, and models used…

6 104 472 37K 473

Download Image

elvis @omarsar0

a year ago

Synthesizing Text-to-SQL Data from Weak and Strong LLMs Proposes integrated synthetic data to build a highly specialized SoTA text-to-SQL model called SENSE. The synthetic data from strong models enhances data diversity while valuable erroneous data from weaker models combined…

3 57 216 16K 139

Download Image

Josep Ferrer @rfeers

a year ago

How Python work in our computer clearly explained👇🏻

2 48 274 29K 240

Download Image

Sahn Lam @sahnlam

a year ago

Caching 101: The Must-Know Caching Strategies Fetching data is 𝘀𝗹𝗼𝘄. Caching speeds things up by storing frequently accessed data for quick reads. But how do you populate and update the cache? That's where strategies come in. 🔍 Read Strategies: 𝗖𝗮𝗰𝗵𝗲 𝗔𝘀𝗶𝗱𝗲 (Lazy…

4 117 550 45K 629

Download Image

Rohan Paul @rohanpaul_ai

a year ago

Uncovers a critical vulnerability in the function calling process of LLMs, introducing a novel "jailbreak function" attack method that exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters. 📌Jailbreak function attack exploits…

6 57 315 28K 272

Download Image

elvis @omarsar0

a year ago

LLM NEWS: New SoTA text-to-image and LLM debut. Major developments include: - SoTA text-to-image models debut (FLUX.1) - Gemini 1.5 Pro leads Chatbot Arena - Self-Reasoning layer enhances RAG accuracy - Meta-judges improve LLMs - Gemma 2 2B outperforms larger models -…

2 39 152 16K 83

Download Image

Ningyu Zhang@ZJU @zxlzr

a year ago

Welcome to attend the tutorial on "Knowledge Editing for Large Language Models" at IJCAI 2024 @IJCAIconf . Here are the details #NLP #AI #KnowledgeEditing #LLMs : Tutorial: Knowledge Editing for Large Language Models Location: Room 1F-Yeongju B Time: 9:00-12:30, August 3, 2024…

1 13 70 6K 24

Download Image

Haihao Shen @HaihaoShen

a year ago

🎯Continued the thread of LLM low-bit quantization around Llama3.1, INC (Intel Neural Compressor), AWQ, and BnB provides the day-0 support, while the INT4 accuracy has *big* difference. See below diagram, and more details in leaderboard: huggingface.co/spaces/Intel/l…