Downloads · 30 days
155
63% of all-time downloads
Deepseek-S3_sq_a05_v2_mlperf6_1
amd/Deepseek-S3_sq_a05_v2_mlperf6_1
Deepseek-S3_sq_a05_v2_mlperf6_1 is a machine learning model from amd. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Model Name: deepseek-ai/DeepSeek-R1 - Version: MLPerf v6.1 - Commit: Close Division Commit
All-time downloads
246
Public
Parameters
339B
366 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors366 GB · 100%
Parameter types
How the weights are stored.
U8332B · 98%
Base models
Model card
From the Hugging Face model README
Quark Team DeepSeek-R1 Model Overview
Model Information For MLPerf
- Model Name: deepseek-ai/DeepSeek-R1
- Version: MLPerf v6.1
- Commit: Close Division Commit
Calibration Dataset
The calibration dataset consists of 500 samples of calibration dataset provided by MLPerf
Quantized Tensors
The following tensors are quantized in each decoder:
- MOE Weights
- Output projection GEMMs
Ignored Layers
The following layers are ignored during quantization:
lm_headq_a_projq_b_projkv_a_proj_with_mqakv_b_projq_a_projq_b_proj
License
Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.
- Type
- deepseek_v3
- Created
- Jul 24, 2026
- Updated
- Jul 31, 2026