Update README.md

README.md

@@ -65,11 +65,18 @@ model-index:
 
 # BrainTransformers: SNN-LLM
 
-Based on BrainTransformers, BrainGPTForCausalLM is a Large Language Model (LLM) implemented using Spiking Neural Networks (SNN). Our technical report will be uploaded to arXiv as soon as possible. We plan to further optimize the model at the operator level and adapt it for hardware compatibility, enabling BrainGPTForCausalLM to be deployed on more energy-efficient SNN hardware devices.
+Based on BrainTransformers, BrainGPTForCausalLM is a Large Language Model (LLM) implemented using Spiking Neural Networks (SNN). We are excited to announce that an initial version of our technical report is now available in our GitHub repository. This early release allows the community to access our findings while the full report undergoes the arXiv review process.
+
+Our comprehensive technical report has been submitted to arXiv and is currently in the "on hold" status, pending review. We will be releasing our findings in stages, with updates and more detailed analyses to follow. The full report will be available on arXiv as soon as the review process is completed.
+
+We plan to further optimize the model at the operator level and adapt it for hardware compatibility, enabling BrainGPTForCausalLM to be deployed on more energy-efficient SNN hardware devices.
+
+The current open-source version retains some floating-point calculations to ensure computational efficiency. We will continue to optimize this. Some detailed explanations are provided in the comments within the source code.
+
+Stay tuned for updates as we continue to refine and expand our research findings.
 
 ## Model Availability
 
-- The current pre-trained model parameters have been published on ModelScope: [DataLinguistic/BrainTransformers-3B-Chat](https://www.modelscope.cn/models/DataLinguistic/BrainTransformers-3B-Chat)
 - The current pre-trained model parameters have been published on Hugging Face.[LumenscopeAI/BrainTransformers-3B-Chat](https://huggingface.co/LumenscopeAI/BrainTransformers-3B-Chat)
 
 ## Repository
@@ -148,4 +155,10 @@ messages = [
 ]
 response = generate_text(messages)
 print(response)
-```
+```
+
+## Acknowledgments
+
+The model was trained using ANN-Base-Qwen2, with a total of three training stages, including SNN-specific neuron synaptic plasticity training. The technical report is still being prepared. Please note that SNN models do not support ANN fine-tuning techniques. We are currently developing specialized fine-tuning code tools for SNN models. Our open-source model has achieved leading SOTA results, and we welcome your stars.
+
+This repository includes a complete transformers package, which can directly replace the transformers package in your development environment. This allows compatibility with our SNN-Base-LLM without affecting existing usage.