baconnier loic's picture

baconnier loic PRO

baconnier

·

AI & ML interests

None yet

Organizations

baconnier's activity

upvoted an article 20 days ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

Jul 29

• 193

upvoted a paper 28 days ago

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment

Paper • 2408.06266 • Published Aug 12 • 9

upvoted 3 articles about 1 month ago

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 55

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 312

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 146

upvoted an article 3 months ago

Article

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

By

•

Jul 9

• 34

upvoted a paper 3 months ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20 • 85

upvoted 2 articles 3 months ago

Article

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

By

•

Jun 19

• 7

Article

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

By

•

Jun 12

• 6

upvoted a paper 4 months ago

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 86

upvoted a collection 5 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

upvoted 2 collections 6 months ago

💥 Laser vs DoRA vs Daser vs LoRA

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

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 Jun 12 • 211

upvoted a paper 8 months ago

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

Paper • 2402.03300 • Published Feb 5 • 67

upvoted a collection 8 months ago

🐶 Beagle

Merges done using mergekit and LazyMergekit: https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb#scrollTo=d5mYzDo1q96y • 8 items • Updated Aug 16 • 6

upvoted a collection 10 months ago

DRAGON Models

Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ..." the leading foundation base models • 20 items • Updated 25 days ago • 44