|
|
--- |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- mlfoundations/dclm-baseline-1.0-parquet |
|
|
--- |
|
|
|
|
|
# Covenant72B |
|
|
|
|
|
**Covenant72B** is the largest permissionless collaboratively trained language |
|
|
model trained entirely from scratch at the 72 billion parameter scale. |
|
|
|
|
|
It is being trained with 20+ globally distributed participants coordinated via |
|
|
decentralized infrastructure on the Bittensor blockchain. |
|
|
|
|
|
**Checkpoint-Two** marks the second release, corresponding to **420 billion |
|
|
tokens processed**. Model files are available in the [Checkpoint-Two |
|
|
branch](https://huggingface.co/tplr/Covenant72B/tree/Checkpoint-Two). Future |
|
|
checkpoints will be updated here. |
|
|
|
|
|
 |
|
|
|
|
|
--- |
|
|
|
|
|
## Training Details |
|
|
|
|
|
| Property | Value | |
|
|
|-----------|--------| |
|
|
| **Model size** | 72B | |
|
|
| **Architecture** | LLaMA-style | |
|
|
| **Target token budget** | 1.2T (420B for current checkpoint) | |
|
|
| **Compute participants** | 20+ | |
|
|
| **Minimal compute per participant** | 8×B200 or equivalent | |
|
|
| **Dataset** | DCLM-baseline | |
|
|
| **Optimizer** | SparseLoCo (communication-efficient optimizer) | |
|
|
|
|
|
--- |
|
|
|
|
|
## Performance on Benchmarks |
|
|
_All results are 0-shot acc-norm (%) unless noted._ |
|
|
|
|
|
| Model | Compute Environment / Permissions | Size | Tokens | ARC-C | ARC-E | PIQA | OpenBookQA | HellaSwag | Winogrande (acc) | MMLU (acc) | |
|
|
|:------|:----------------------------------|------:|--------:|------:|------:|------:|------------:|-----------:|-------------:|------:| |
|
|
| **Intellect-1** | Internet / Whitelist | 10B | 1T | 44.8 | 71.6 | 77.7 | 43.6 | 70.5 | 63.1 | 32.7 | |
|
|
| **Psyche Consilience-7Y9** | Internet / Whitelist | 40B | 1.2T | 31.1 | 55.8 | 76.1 | 34.8 | 63.7 | 57.0 | 24.2 | |
|
|
| **Covenant72B (Checkpoint-Two)** | Internet / Permissionless | 72B | **420B** | **53.84** | **77.74** | **80.58** | **44.60** | **77.08** | **71.43** | **47.49** | |
|
|
| **LLM360 K2 ckpt_108** | Centralized Cluster | 65B | 420B | 45.73 | 70.54 | 80.90 | 43.20 | 78.23 | 71.90 | 50.01 | |
|
|
| **LLM360 K2 Stage 1** | Centralized Cluster | 65B | 1.4T | 53.84 | 75.93 | 82.48 | 48.00 | 82.81 | 76.64 | 63.90 | |
|
|
| **LLaMA-2-7B** | Centralized Cluster | 7B | 2T | 45.90 | 74.58 | 75.92 | 44.20 | 75.92 | 68.90 | 40.86 | |
|
|
| **LLaMA-2-70B** | Centralized Cluster | 70B | 2T | 57.59 | 80.77 | 82.92 | 48.60 | 83.86 | 77.58 | 65.56 | |
|
|
|
|
|
--- |
|
|
|
|
|
For more details, refer to [Checkpoint One on Templar Research](https://templarresearch.substack.com/p/checkpoint-one). |
|
|
|
