matttreed / diloco-simLinks
☆19Updated 4 months ago
Alternatives and similar repositories for diloco-sim
Users that are interested in diloco-sim are comparing it to the libraries listed below
Sorting:
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆100Updated 2 months ago
- look how they massacred my boy☆63Updated 7 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- ☆44Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated 2 months ago
- ☆27Updated 10 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 7 months ago
- Lego for GRPO☆28Updated last week
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆88Updated last week
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆67Updated 2 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆66Updated last month
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- Simple repository for training small reasoning models☆31Updated 3 months ago
- ☆38Updated 10 months ago
- Collection of autoregressive model implementation☆85Updated last month
- Latent Large Language Models☆18Updated 9 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆76Updated last month
- Compiling useful links, papers, benchmarks, ideas, etc.☆46Updated 2 months ago
- A 7B parameter model for mathematical reasoning☆36Updated 3 months ago
- ☆131Updated 2 months ago
- Code for the paper "Function-Space Learning Rates"☆20Updated last month
- Collection of LLM completions for reasoning-gym task datasets☆22Updated last week
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆45Updated last month
- Fork of Flame repo for training of some new stuff in development☆13Updated last week
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆59Updated 7 months ago
- DeMo: Decoupled Momentum Optimization☆188Updated 6 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year
- ☆79Updated 9 months ago
- ☆25Updated 4 months ago
- Train, tune, and infer Bamba model☆127Updated last month