Distillation results for models compressed with Puzzletron MIP-based heterogeneous pruning, followed by Megatron-Bridge knowledge distillation.
| Model | File |
|---|---|
| Llama-3.1-8B-Instruct and Qwen3-8B | Llama-3.1-8B-Instruct.md |
Distillation results for models compressed with Puzzletron MIP-based heterogeneous pruning, followed by Megatron-Bridge knowledge distillation.
| Model | File |
|---|---|
| Llama-3.1-8B-Instruct and Qwen3-8B | Llama-3.1-8B-Instruct.md |