S1: The $6 R1 Competitor?
AI/ML
S1: The $6 R1 Competitor?
Tim Kellogg shares his notes on a new paper, [s1: Simple test-time scaling](https://arxiv.org/abs/2501.19393), which describes an inference-scaling model fine-tuned on top of Qwen2.5-32B-Instruct for just $6 - the cost for …
DeepSeek Debates: Chinese Leadership On Cost, True Training Cost, Closed Model Margin Impacts
The DeepSeek Narrative Takes the World by Storm DeepSeek took the world by storm. For the last week, DeepSeek has been the only topic that anyone in the world wants to talk about. As it currently s…
Is MLX the best Fine Tuning Framework?
🚀 Want to fine-tune AI models on your Mac without cloud services? As an ex-Ollama developer, I'll show you how to use Apple's MLX framework to fine-tune mod...
Blaizzy/mlx-vlm: MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.
MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX. - Blaizzy/mlx-vlm
Creating a LLM-as-a-Judge that drives business results
Hamel Husain's sequel to [Your AI product needs evals](https://hamel.dev/blog/posts/evals/). This is _packed_ with hard-won actionable advice. Hamel warns against using scores on a 1-5 scale, instead promoting an alternative he …
What We Learned from a Year of Building with LLMs (Part I)
RAFT: A new way to teach LLMs to be better at RAG
In this article, we will look at the limitations of RAG and domain-specific Fine-tuning to adapt LLMs to existing knowledge and how a team of UC Berkeley..
WeihaoTan/TWOSOME: Implementation of TWOSOME
flowersteam/Grounding_LLMs_with_online_RL: We perform functional grounding of LLMs' knowledge in BabyAI-Text
KhoomeiK/LlamaGym: Fine-tune LLM agents with online reinforcement learning
Fine-tune LLM agents with online reinforcement learning - KhoomeiK/LlamaGym
Finetuning Open-Source LLMs
This video offers a quick dive into the world of finetuning Large Language Models (LLMs). This video covers - common usage scenarios for pretrained LLMs- par...
Fast Llama 2 on CPUs With Sparse Fine-Tuning and DeepSparse - Neural Magic
Key Takeaways We expanded our Sparse Fine-Tuning research results to include Llama 2. The results include 60% sparsity with INT8 quantization and no drop in accuracy. DeepSparse now supports accelerated inference of sparse-quantized Llama 2 models, with inference speeds 6-8x faster over the baseline at 60-80% sparsity. We used some interesting algorithmic techniques in order
jondurbin/airoboros: Customizable implementation of the self-instruct paper.