alphaXiv / paper-implementationsLinks
Clean, reusable paper implementations for trending papers on alphaXiv
☆84Updated this week
Alternatives and similar repositories for paper-implementations
Users that are interested in paper-implementations are comparing it to the libraries listed below
Sorting:
- lossily compress representation vectors using product quantization☆59Updated last month
- A collection of lightweight interpretability scripts to understand how LLMs think☆71Updated this week
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆121Updated 2 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆168Updated 4 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆76Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 8 months ago
- Source code for the collaborative reasoner research project at Meta FAIR.☆111Updated 8 months ago
- RLP: Reinforcement as a Pretraining Objective☆213Updated 2 months ago
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆31Updated 6 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆241Updated 2 weeks ago
- EvaByte: Efficient Byte-level Language Models at Scale☆111Updated 8 months ago
- ☆47Updated this week
- KernelBench v2: Can LLMs Write GPU Kernels? - Benchmark with Torch -> Triton (and more!) problems☆21Updated 5 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆34Updated 8 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆108Updated 9 months ago
- ☆36Updated 4 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 2 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆26Updated last week
- Code and training scripts for FlexOlmo☆118Updated last week
- 🤖 Complete reproduction of 'AlphaGo Moment for Model Architecture Discovery' using MLX-LM instead of GPT-4. Autonomous neural architectu…☆26Updated 4 months ago
- ☆131Updated last year
- 🧬 The Huxley-Gödel Machine☆314Updated 3 weeks ago
- Simple & Scalable Pretraining for Neural Architecture Research☆305Updated 2 weeks ago
- ☆92Updated last month
- ☆59Updated last month
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆124Updated 4 months ago
- Official Repository for Task-Circuit Quantization☆24Updated 6 months ago
- ☆55Updated last year
- ☆79Updated 2 months ago
- ☆29Updated last month