| license: apache-2.0 | |
| datasets: | |
| - abideen/Cosmopedia-100k-pretrain | |
| language: | |
| - en | |
| tags: | |
| - llama3 | |
| - meta | |
| - bitnet | |
| - full bitnet | |
| needs work. it appears that the 1bit models are far less efficient when scare in terms of memory usage |
| license: apache-2.0 | |
| datasets: | |
| - abideen/Cosmopedia-100k-pretrain | |
| language: | |
| - en | |
| tags: | |
| - llama3 | |
| - meta | |
| - bitnet | |
| - full bitnet | |
| needs work. it appears that the 1bit models are far less efficient when scare in terms of memory usage |