sasa2000/Marco-Nano-Instruct-REAP-6B-A0.6B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
5be39aeba1ad038881054983cd0a1c47436f48bd
Marco-Nano-Instruct-REAP-6B…/README.md
ModelHub XC 5be39aeba1 初始化项目，由ModelHub XC社区提供模型 
Model: sasa2000/Marco-Nano-Instruct-REAP-6B-A0.6B
Source: Original Platform
2026-08-28 17:13:52 +08:00

1.0 KiB
Raw Blame History

license, base_model, library_name, pipeline_tag, tags
license base_model library_name pipeline_tag tags
apache-2.0 ATH-MaaS/Marco-Nano-Instruct transformers text-generation
reap
pruning
qwen3_moe
moe
safetensors

Marco-Nano-Instruct REAP Pruned 0.25

This is a pruned derivative of ATH-MaaS/Marco-Nano-Instruct, produced with CerebrasResearch/reap layerwise REAP pruning in a Codex-assisted experiment (GPT5.5 xhigh based).

Details

  • Pruning method: REAP layerwise pruning
  • Requested compression ratio: 0.25
  • Experts retained: 174
  • Experts per token: 8
  • Calibration dataset: theblackcat102/evol-codealpaca-v1
  • model_max_length: 2048
  • batches_per_category: 128
  • batch_size: 1
  • batch_group_size: 8
  • Format: safetensors

Notes

This checkpoint was created for a low-resource pruning experiment on a 6GB VRAM environment. Benchmark evaluation was not run. A short prompt smoke check showed usable English output, but Japanese and Chinese outputs may still show repetition, self-continuation, or wording artifacts.