| datasets: | |
| - cerebras/SlimPajama-627B | |
| language: | |
| - en | |
| This is the trained 1.3 billion parameter LLAMA-2 architecture model for the work [Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining](https://arxiv.org/pdf/2410.08102) |
| datasets: | |
| - cerebras/SlimPajama-627B | |
| language: | |
| - en | |
| This is the trained 1.3 billion parameter LLAMA-2 architecture model for the work [Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining](https://arxiv.org/pdf/2410.08102) |