|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- PrimeIntellect/fineweb-edu |
|
- PrimeIntellect/fineweb |
|
- PrimeIntellect/StackV1-popular |
|
- mlfoundations/dclm-baseline-1.0-parquet |
|
- open-web-math/open-web-math |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# INTELLECT-1-step-17000 |
|
|
|
This is an intermediate checkpoint of INTELLECT-1. You can find the [final version](https://huggingface.co/PrimeIntellect/INTELLECT-1) as well as the [instruct one](https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct) |
|
|
|
| | Step | Model URL | |
|
|---|------|-----------| |
|
| -> | 17000 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-17000 | |
|
| | 28600 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-28600 | |
|
| | 39200 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-39200 | |
|
| | 49200 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-49200 | |
|
| | 59200 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-59200 | |
|
| | 69200 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-69200 | |
|
| | 78000 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-78000 | |
|
| | 88000 | https://huggingface.co/PrimeIntellect/INTELLECT-1-step-88000 | |
|
|
|
## **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](https://github.com/PrimeIntellect-ai/prime), 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](https://github.com/PrimeIntellect-ai/prime). |
|
|
|
## **Model Details** |
|
- **Model Contributors**: samsja, Prime Intellect, Arcee AI, kotaro, skre_0, marlo, rodeo, Herb, Olas, superchillen, Hugging Face, mev_pete, 0xfr_, dj, primeprimeint1234, Marco Giglio, realtek, Hyperbolic, hecataeus, NWO, Virtual Machine, droll, SemiAnalysis, _waiting__, toptickcrypto, sto, Johannes, washout_segment_0b, klee |
|
- **Release Date**: 29 Nov 2024 |
|
- **Model License**: Apache 2.0 |
|
|
|
## **Technical Specifications** |
|
| **Parameter** | **Value** | |
|
|----------------------|------------------------| |
|
| Parameter Size | 10B | |
|
| Number of Layers | 42 | |
|
| Number of Attention Heads | 32 | |
|
| Hidden Size | 4096 | |
|
| Context Length | 8192 | |
|
| Vocabulary Size | 128256 | |
|
|
|
## **Citations** |
|
If you use this model in your research, please cite it as follows: |
|
``` |
|
@article{} |
|
``` |
