Many-shot jailbreaking
•
6
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
Aurora-M: The First Open Source Biden-Harris Executive Order Red teamed Multilingual Language Model
•
7
Gecko: Versatile Text Embeddings Distilled from Large Language Models
•
5
Finetune Mixtral 8x7B with AutoTrain
•
10
How do Textual Inversion tokens destroy prompts?
•
4
Experiments with Bitnet 1.5 (~ngmi~)
•
7
Create Mixtures of Experts with MergeKit
•
27
Elevate Responses: RAG with LlamaIndex & MongoDB
•
4
Samantha Mistral Instruct 7b - Comprehensive Bulleted Notes
•
8
Policy Questions Blog 1: AI Data Transparency Remarks for NAIAC Panel 📚🔍⚖️
•
3
Protein similarity and Matryoshka embeddings
•
2
A brief analysis of automerger data, feat. SLERP and DARE-TIES LLM merging
•
2
Data exploration and filtering with Nomic Atlas
•
6
Giskard Bot: Identifying robustness, performance and ethical vulnerabilities in the Top 10 Most Popular Hugging Face Models
•
2
Releasing Common Corpus: the largest public domain dataset for training LLMs
•
30
What's Automatic Differentiation?
•
26
Dive Deeper into Yi-9B
•
6
Sparse Mixture of Experts Language Model from Scratch: Extending makeMoE with Expert Capacity
•
13
VideoMamba: State Space Model for Efficient Video Understanding
•
2
Better RAG 3: The text is your friend
•
13