Feynman Innovations's picture

Feynman Innovations

ajibawa-2023

·

AjinkyaBawase

AI & ML interests

LLM, RL, DL, ML, AGI. Developing LLMs (preferably fully fine tuned ) for various use cases.

Recent Activity

reacted to singhsidhukuldeep's post with 🔥 2 days ago

Exciting Research Alert: Revolutionizing Complex Information Retrieval! A groundbreaking paper from researchers at MIT, AWS AI, and UPenn introduces ARM (Alignment-Oriented LLM-based Retrieval Method), a novel approach to tackle complex information retrieval challenges. >> Key Innovations Information Alignment The method first decomposes queries into keywords and aligns them with available data using both BM25 and embedding similarity, ensuring comprehensive coverage of information needs. Structure Alignment ARM employs a sophisticated mixed-integer programming solver to identify connections between data objects, exploring relationships beyond simple semantic matching. Self-Verification The system includes a unique self-verification mechanism where the LLM evaluates and aggregates results from multiple retrieval paths, ensuring accuracy and completeness. >> Performance Highlights The results are impressive: - Outperforms standard RAG by up to 5.2 points in execution accuracy on Bird dataset - Achieves 19.3 points higher F1 scores compared to existing approaches on OTT-QA - Reduces the number of required LLM calls while maintaining superior retrieval quality >> Technical Implementation The system uses a three-step process: 1. N-gram indexing and embedding computation for all data objects 2. Constrained beam decoding for information alignment 3. Mixed-integer programming optimization for structure exploration This research represents a significant step forward in making complex information retrieval more efficient and accurate. The team's work demonstrates how combining traditional optimization techniques with modern LLM capabilities can solve challenging retrieval problems.

reacted to Tonic's post with 🔥 2 days ago

🙋🏻‍♂️hey there folks , Goedel's Theorem Prover is now being demo'ed on huggingface : https://huggingface.co/spaces/Tonic/Math give it a try !

reacted to hba123's post with 🔥 2 days ago

We developed a method that ensures almost-sure safety (i.e., safety with probability approaching 1). We proved this result. We then, present a practical implementation which we call InferenceGuard. InferenceGuard has impressive practical results: 91.04% on Alpaca-7B and 100% safety results on Beaver 7B-v3. Now, it is easy to get high safety results like those if we want a dumb model, e.g., just don't answer or answer with EOS and so on. However, our goal is not to only have safe results, but also to make sure that the rewards are high - we want a good trade-off between safety and rewards! That's exactly, what we show. InferenceGuard achieves that! Check it out: https://huggingface.co/papers/2502.01208

View all activity

Organizations

ajibawa-2023's activity

New activity in ajibawa-2023/Code-290k-ShareGPT 3 months ago

How is this dataset created?

#3 opened 3 months ago by

New activity in ajibawa-2023/Python-Code-13B 3 months ago

Adding `safetensors` variant of this model

#2 opened 3 months ago by

New activity in ajibawa-2023/General-Stories-Collection 4 months ago

Which models were used to generate this dataset?

#2 opened 4 months ago by

New activity in Vezora/Open-Critic-GPT 6 months ago

Thanks for credit!

#3 opened 6 months ago by

New activity in ajibawa-2023/Young-Children-Storyteller-Mistral-7B 7 months ago

GGUFs

#2 opened 10 months ago by

New activity in ajibawa-2023/Code-Llama-3-8B 7 months ago

Very bad model

#2 opened 7 months ago by

New activity in ajibawa-2023/Children-Stories-Collection 7 months ago

Information and DOI request

#1 opened 9 months ago by

New activity in ajibawa-2023/Young-Children-Storyteller-Mistral-7B 8 months ago

Update README.md

#4 opened 8 months ago by

New activity in open-llm-leaderboard-old/requests 9 months ago

Eval Failed

#146 opened 9 months ago by

New activity in ajibawa-2023/Maths-College 9 months ago

How are the texts generated?

#1 opened 9 months ago by

New activity in ajibawa-2023/Code-Llama-3-8B 9 months ago

Thank you for making this!

#1 opened 9 months ago by

New activity in ajibawa-2023/Maths-Grade-School 9 months ago

[bot] Conversion to Parquet

#1 opened 9 months ago by

parquet-converter

New activity in open-llm-leaderboard-old/requests 9 months ago

Eval Failed

#124 opened 9 months ago by

New activity in ajibawa-2023/Scarlett-Llama-3-8B-v1.0 9 months ago

Adding Evaluation Results

#1 opened 9 months ago by

leaderboard-pr-bot

New activity in ajibawa-2023/Uncensored-Frank-Llama-3-8B 9 months ago

Adding Evaluation Results

#1 opened 9 months ago by

leaderboard-pr-bot

New activity in ajibawa-2023/Code-Mistral-7B 9 months ago

impressed with consistency in chat

#3 opened 9 months ago by

New activity in ajibawa-2023/Code-Mistral-7B 10 months ago

Adding `safetensors` variant of this model

#2 opened 10 months ago by

New activity in open-llm-leaderboard-old/requests 10 months ago

Why eval failed for ajibawa-2023/General-Stories-Mistral-7B

#120 opened 10 months ago by

commented a paper 10 months ago

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Paper • 2402.09844 • Published Feb 15, 2024 • 21 •

New activity in ajibawa-2023/Scarlett-Llama-3-8B 10 months ago

Adding Evaluation Results

#1 opened 10 months ago by

leaderboard-pr-bot