marin-community / marinLinks
Open-source framework for the research and development of foundation models.
β501Updated this week
Alternatives and similar repositories for marin
Users that are interested in marin are comparing it to the libraries listed below
Sorting:
- πΎ OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.β535Updated this week
- PyTorch building blocks for the OLMo ecosystemβ305Updated last week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β166Updated 3 months ago
- β222Updated 2 weeks ago
- Understand and test language model architectures on synthetic tasks.β233Updated 3 weeks ago
- β827Updated this week
- Sparsify transformers with SAEs and transcodersβ640Updated this week
- Physics of Language Models, Part 4β248Updated 2 months ago
- Best practices & guides on how to write distributed pytorch training codeβ500Updated last week
- β283Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jaxβ669Updated this week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"β536Updated last week
- Async RL Training at Scaleβ709Updated this week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"β330Updated 11 months ago
- A bibliography and survey of the papers surrounding o1β1,209Updated 11 months ago
- β104Updated this week
- A project to improve skills of large language modelsβ581Updated last week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsβ¦β342Updated 10 months ago
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewardsβ1,181Updated 2 weeks ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.β236Updated this week
- Training APIβ158Updated this week
- A MAD laboratory to improve AI architecture designs π§ͺβ131Updated 10 months ago
- Dion optimizer algorithmβ366Updated 2 weeks ago
- Open source interpretability artefacts for R1.β161Updated 5 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.β296Updated 2 months ago
- An extension of the nanoGPT repository for training small MOE models.β197Updated 7 months ago
- Extract full next-token probabilities via language model APIsβ247Updated last year
- β527Updated last year
- Post-training with Tinkerβ1,028Updated this week
- Reproducible, flexible LLM evaluationsβ256Updated this week