PrimeIntellect/INTELLECT-1-step-69200

INTELLECT-1-step-69200

This is an intermediate checkpoint of INTELLECT-1. You can find the final version as well as the instruct one

Model Overview

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

INTELLECT-1 was trained on up to 14 concurrent nodes distributed across 3 continents, with contributions from 30 independent community contributors providing compute. The training code utilizes the prime framework, a scalable distributed training framework designed for fault-tolerant, dynamically scaling, high-perfomance training on unreliable, globally distributed workers. The key abstraction that allows dynamic scaling is the ElasticDeviceMesh which manages dynamic global process groups for fault-tolerant communication across the internet and local process groups for communication within a node The global all-reduce was done with custom int8 all-reduce kernels to reduce the communication payload required, greatly reducing the communication overhead.

For more detailed technical insights, please refer to our technical paper.

Model Details

• —Model Contributors: samsja, Prime Intellect, Arcee AI, kotaro, skre0, marlo, rodeo, Herb, Olas, superchillen, Hugging Face, mevpete, 0xfr, dj, primeprimeint1234, Marco Giglio, realtek, Hyperbolic, hecataeus, NWO, Virtual Machine, droll, SemiAnalysis, waiting_, toptickcrypto, sto, Johannes, washoutsegment_0b, klee
• —Release Date: 29 Nov 2024
• —Model License: Apache 2.0

Technical Specifications

Citations

If you use this model in your research, please cite it as follows:

@article{}