Correct minor typos and ensure consistency in terminology in `README.md` and `README_WEIGHTS.md`.
* **README.md**
- Correct minor typos in the text.
- Ensure consistency in terminology across the document.
* **README_WEIGHTS.md**
- Correct minor typos in the text.
- Ensure consistency in terminology across the document.
---
For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/deepseek-ai/DeepSeek-V3?shareId=XXXX-XXXX-XXXX-XXXX).
This file includes detailed citation information for the DeepSeek-V3 project, such as authors, DOI, license, and key project details. It enables users to properly cite the work and promotes better academic and professional attribution.
* handle missing scale_inv_name
Fixed an issue where `weight` and `weight_scale_inv` (e.g. `model.layers.39.mlp.experts.92.gate_proj.weight` and `model.layers.39.mlp.experts.92.gate_proj.weight_scale_inv`) were not in the same SafeTensor, causing an assertion error due to scale_inv_name not being in the state_dict.
* sort filename to reduce memory costs
* Add CUDA cache clearing in memory management
Added torch.cuda.empty_cache() to free up unused memory on the GPU,