---
license: mit
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
tags:
- text-generation
- lmul
- research
- experimental
- qwen3
---

# L-Mul Optimized: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

This is a modified version of DeepSeek AI's [DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B) model. The modification consists of replacing the standard attention mechanism with one that uses a custom, approximate matrix multiplication algorithm termed "L-Mul".

This work was performed as part of a research project to evaluate the performance and accuracy trade-offs of algorithmic substitutions in transformer architectures.

**This model is intended strictly for educational and scientific purposes.**

## Model Description

The core architecture of `deepseek-ai/DeepSeek-R1-0528-Qwen3-8B` is preserved. However, the standard `Qwen3Attention` modules have been dynamically replaced with a custom version that utilizes the `l_mul_attention` function for its core computations. This function is defined in the `lmul.py` file included in this repository.

-   **Base Model:** [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
-   **Modification:** Replacement of standard attention with L-Mul approximate attention.
-   **Primary Use-Case:** Research and educational analysis of algorithmic impact on LLMs.

## How to Get Started

To use this model, you must use the `trust_remote_code=True` flag when loading it. This is required to execute the custom `lmul.py` file that defines the new attention mechanism.

You can load the model directly from this repository using the `transformers` library:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Define the repository ID for the specific model
repo_id = "Peacemann/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B_LMUL" # Replace with the correct repo ID if different

# Load the tokenizer and model, trusting the remote code to load lmul.py
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

# Example usage
prompt = "The L-Mul algorithm is an experimental method for..."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

For high-throughput inference, you can use `vLLM`:

```python
from vllm import LLM

repo_id = "Peacemann/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B_LMUL" # Replace with the correct repo ID
llm = LLM(model=repo_id, trust_remote_code=True)
```

## Intended Uses & Limitations

This model is intended for researchers and students exploring the internal workings of LLMs. It is a tool for visualizing and analyzing the effects of fundamental algorithmic changes.

**This model is NOT intended for any commercial or production application.**

The modification is experimental. The impact on the model's performance, safety alignment, accuracy, and potential for generating biased or harmful content is **unknown and untested**. It inherits all limitations and biases of the original `DeepSeek-R1-0528-Qwen3-8B` model, and its behavior may be altered in unpredictable ways.

## Licensing Information

The use of this model is subject to the original **MIT License**. By using this model, you agree to the terms outlined in the license. The license can be found on the base model's Hugging Face page.