Downloads · 30 days
4
10% of all-time downloads
24b1051-Week04-Compression-20-Submission02
ParthivMEV/24b1051-Week04-Compression-20-Submission02
24b1051-Week04-Compression-20-Submission02 is a machine learning model from ParthivMEV. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Public compressed checkpoint for the CS6013 Efficient AI Week04 Track 1 submission.
All-time downloads
40
Public
Repo size
1.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 99%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026
- SHA
- e5029d2c
Base models
Model card
From the Hugging Face model README
24b1051 Week04 Track1 20% Submission02
Public compressed checkpoint for the CS6013 Efficient AI Week04 Track 1 submission.
- Base model: Qwen/Qwen3-4B-Instruct-2507
- Base revision: cdbee75f17c01a7cc42f958dc650907174af0554
- Hugging Face repository: https://huggingface.co/ParthivMEV/24b1051-Week04-Compression-20-Submission02
- Method: packed groupwise NF3 with selective packed W4, FP16 scales, group size 128
- BF16 baseline weights: 8044982000 bytes
- Compressed weights: 1596568736 bytes
- Ratio: 19.84552279%
- Reconstruction code: https://github.com/Parthiv-MEV/CS6013/tree/main/24b1051/Week04/Compression_20/Submission02
Use the submission's dequantize_to_bf16.py to reconstruct a standard BF16 Hugging Face checkpoint.
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026