SeeMoE: Implementing a MoE Vision Language Model from Scratch
By
•
•
34Shape Rotation 101: An Intro to Einsum and Jax Transformers
By
•
•
5Open-source embeddings and LLMs outperform Gemini and OpenAI for Web Navigation while being faster and cheaper
By
•
•
7Recommendation to Revisit the Diffuser Default LoRA Parameters
By
•
•
11Introducing Synthetic Data Workshop: Your Gateway to Easy Synthetic Dataset Creation
By
•
•
12Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖
By
•
•
26Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations
By
•
•
17Unveiling CIVICS: A New Dataset for Examining Cultural Values in Language Models
By
•
•
12Introducing the Ultimate SEC LLM: Revolutionizing Financial Insights with Llama-3-70B
By
•
•
7Train a Terrible Tic-Tac-Toe AI
By
•
•
3Thoughts on LoRA Training Pt 2: Where to Train
By
•
•
14Thoughts on LoRA Training #1
By
•
•
33MobileNet-V4 (now in timm)
By
•
•
48Against mixing environment setup with code
By
•
SwanLab and Transformers: Power Up Your NLP Experiments
By
•
•
6CryptGPT: Privacy-Preserving Language Models Using Vigenere Cipher (Part 1)
By
•
•
6The CVPR Survival Guide: Discovering Research That's Interesting to YOU!
By
•
•
9Uncensor any LLM with abliteration
By
•
•
642Low Latency CPU Based Educational Value Classifier With Generic Educational Value
By
•
•
9An Optimal Lossy Variant of Speculative Decoding
By
•
•
2