Downloads · 30 days
6
11% of all-time downloads
Marco-Nano-Instruct-REAP-4B-A0.6B
sasa2000/Marco-Nano-Instruct-REAP-4B-A0.6B
Marco-Nano-Instruct-REAP-4B-A0.6B is a text generation model from sasa2000. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
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).
All-time downloads
54
Public
Parameters
4.2B
8.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_moe
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026
- SHA
- 74d37083
Try a prompt
Base models
Model card
From the Hugging Face model README
Marco-Nano-Instruct REAP Pruned 0.50
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:
0.50 - Experts retained:
116 - Experts per token:
8 - Calibration dataset:
theblackcat102/evol-codealpaca-v1 model_max_length:2048batches_per_category:128batch_size:1batch_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 the strongest degradation among the tested Marco-Nano pruning ratios, including repetition and multilingual instability.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_moe
- License
- apache-2.0
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026