---
title: DeepSeek-R1-0528-BF16
canonical_url: "https://www.modelscope.ai/models/AMD/DeepSeek-R1-0528-BF16"
md_url: "https://www.modelscope.ai/models/AMD/DeepSeek-R1-0528-BF16.md"
repository: AMD/DeepSeek-R1-0528-BF16
last_updated: 2026-03-05
license: mit
model_type:
  - deepseek_v3
architectures:
  - DeepseekV3ForCausalLM
base_model:
  - unsloth/DeepSeek-R1-0528-BF16
base_model_relation: finetune
parameters: 684.5B
tensor_type:
  - BF16
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 156
stars: 0
---

# DeepSeek-R1-0528-BF16

> DeepSeek-R1-0528-BF16 - An open-source model by AMD on ModelScope. Model Architecture: DeepSeek-R1-0528 Input: Text Output: Text Supported Hardware Microarchitecture: AMD MI350/MI355 ROCm: 7.0 PyTorch: 2.8.0 Transformers: 4.56.1 Operating System(s): Linux…

AMD/DeepSeek-R1-0528-BF16 is a 684.5B-parameter machine learning model on ModelScope. licensed under mit. derived from unsloth/DeepSeek-R1-0528-BF16.

- **Repository**: AMD/DeepSeek-R1-0528-BF16
- **License**: mit
- **Parameters**: 684.5B
- **Base model**: unsloth/DeepSeek-R1-0528-BF16
- **Downloads**: 156
- **Stars**: 0
- **Last updated**: 2026-03-05

Source: https://www.modelscope.ai/models/AMD/DeepSeek-R1-0528-BF16

---

# Model Overview

- **Model Architecture:** DeepSeek-R1-0528
  - **Input:** Text
  - **Output:** Text
- **Supported Hardware Microarchitecture:** AMD MI350/MI355
- **ROCm**: 7.0
- **PyTorch**: 2.8.0
- **Transformers**: 4.56.1
- **Operating System(s):** Linux
- **Inference Engine:** [SGLang](https://docs.sglang.ai/)/[vLLM](https://docs.vllm.ai/en/latest/)

# Model Details

In the original `modeling_deepseek.py` file from the `unsloth/DeepSeek-R1-0528-BF16` model, there is no definition or implementation of the MTP (Multi-Token-Predictor) layer. As a result, when you load the original model, there is no MTP layer included, and MTP-specific quantization cannot be performed.

To enable MTP layer loading and quantization, this model is adapted from `unsloth/DeepSeek-R1-0528-BF16` by adding an MTP layer in the `modeling_deepseek.py` file. With this modification, it is possible to use [AMD-Quark](https://quark.docs.amd.com/latest/index.html) to quantize the DeepSeek-R1-0528 model with the MTP layer included.

**Important Notes:**
- When loading this model, you must set `trust_remote_code=True` to ensure that changes related to the MTP layer in `modeling_deepseek.py` take effect.
- After loading this model with `transformers`, **evaluation should NOT be performed directly**. The reason is that the forward function for the added MTP layer in `modeling_deepseek.py` is implemented only for calibration during the quantization process, so computation is not guaranteed to be the same as the original DeepSeek-R1-0528.
- Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
- To skip quantization for the MTP layers, set `exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj *shared_head.head model.layers.61.*"`.

Below is an example of how to quantize this model:

```bash
cd Quark/examples/torch/language_modeling/llm_ptq/
exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj *shared_head.head" 
python3 quantize_quark.py --model_dir $MODEL_DIR \
                          --quant_scheme w_mxfp4_a_mxfp4 \
                          --num_calib_data 32 \
                          --output_dir $output_dir \
                          --exclude_layers $exclude_layers \
                          --dataset pileval \
                          --multi_gpu \
                          --model_export hf_format \
                          --trust_remote_code \
                          --skip_evaluation \
                          --seq_len 512
```
For further details or issues, please refer to the [AMD-Quark](https://quark.docs.amd.com/latest/index.html) documentation or contact the respective developers.

# License
Modifications Copyright(c) 2025 Advanced Micro Devices, Inc. All rights reserved.