| # FORGE-3B dependencies | |
| torch>=2.3.0 | |
| transformers>=4.41.0 | |
| datasets>=2.19.0 | |
| tokenizers>=0.19.1 | |
| wandb==0.17.0 | |
| deepspeed>=0.14.4 | |
| flash-attn>=2.5.8 | |
| einops==0.8.0 | |
| accelerate==0.30.1 | |
| bitsandbytes==0.43.1 | |
| mamba-ssm>=1.2.0 | |
| causal-conv1d>=1.3.0 | |
| numpy>=1.24.0 | |
| triton>=2.1.0 | |
| xerv-crayon | |