baconnier loic's picture

baconnier loic PRO

baconnier

·

AI & ML interests

None yet

Organizations

baconnier's activity

upvoted an article 5 days ago

Article

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

By

•

3 days ago

• 22

upvoted a paper 7 days ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published 9 days ago • 74

upvoted an article 10 days ago

Article

Introducing the Ultimate SEC LLM: Revolutionizing Financial Insights with Llama-3-70B

By

•

10 days ago

• 6

upvoted an article 17 days ago

Article

Building a Vision Mixture-of-Expert Model from several fine-tuned Phi-3-Vision Models

By

•

17 days ago

• 4

upvoted an article 20 days ago

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 43

upvoted a paper about 1 month ago

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 79

upvoted 2 collections 3 months ago

Unmixtraled experts

This collections contains all 8 experts of Mixtral 8x22B converted to single dense 22B models. The models are intended as basis for merges or finetune • 9 items • Updated Apr 11 • 1

💥 Laser vs DoRA vs Daser vs LoRA

Comparison of different PEFT techniques of NeuralMonarch. • 4 items • Updated Mar 22 • 5

upvoted a collection 4 months ago

Model Merging

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated 16 days ago • 188

upvoted a paper 5 months ago

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5 • 66

upvoted a collection 5 months ago

🐶 Beagle

Merges done using mergekit and LazyMergekit: https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb#scrollTo=d5mYzDo1q96y • 8 items • Updated May 27 • 6

upvoted a collection 7 months ago

DRAGON Models

Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ..." the leading foundation base models • 11 items • Updated Feb 3 • 42