tanmaysachan / splitcompute
Split model weights and execute partially
☆3Updated 8 months ago
Alternatives and similar repositories for splitcompute:
Users that are interested in splitcompute are comparing it to the libraries listed below
- Because it's there.☆15Updated 6 months ago
- ☆20Updated 4 months ago
- Using modal.com to process FineWeb-edu data☆20Updated 3 weeks ago
- Verbosity control for AI agents☆60Updated 10 months ago
- Small, simple agent task environments for training and evaluation☆18Updated 4 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆31Updated last month
- ☆38Updated 8 months ago
- Simple orchestration for EC2 spot containers☆20Updated 6 months ago
- ☆48Updated last year
- Sphynx Hallucination Induction☆53Updated 2 months ago
- Compiling useful links, papers, benchmarks, ideas, etc.☆41Updated 2 weeks ago
- NLP with Rust for Python 🦀🐍☆61Updated 9 months ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- Training code for Sparse Autoencoders on Embedding models☆38Updated last month
- A better way of testing, inspecting, and analyzing AI Agent traces.☆30Updated this week
- ☆38Updated last month
- look how they massacred my boy☆63Updated 5 months ago
- Stream of my favorite papers and links☆41Updated last week
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Benchmark structured generation libraries☆26Updated 5 months ago
- A miniature version of Modal☆20Updated 9 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆56Updated last week
- Quickly and securely turn any Linux box into a build and deployment assistant☆24Updated 5 months ago
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆26Updated 4 months ago
- ☆17Updated 2 weeks ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆26Updated 3 weeks ago
- A lightweight evaluation suite tailored specifically for assessing Indic LLMs across a diverse range of tasks☆33Updated 9 months ago
- a pipeline for using api calls to agnostically convert unstructured data into structured training data☆30Updated 6 months ago
- ☆18Updated this week
- A fast minimalistic implementation of guided generation on Apple Silicon using Outlines and MLX☆53Updated last year