Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,15 @@ The model is trained on **1.4 million high-quality Open-PerfectBlend instruction
|
|
| 18 |
- **High Accuracy Guarantee**: Maintaining 93%+ accuracy on mainstream benchmarks
|
| 19 |
- **Production-Grade Optimization**: Achieving 3954 tokens/s output throughput on single NVIDIA H200
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## Performance
|
| 22 |
|
| 23 |
### Speculative Sampling Efficiency
|
|
|
|
| 18 |
- **High Accuracy Guarantee**: Maintaining 93%+ accuracy on mainstream benchmarks
|
| 19 |
- **Production-Grade Optimization**: Achieving 3954 tokens/s output throughput on single NVIDIA H200
|
| 20 |
|
| 21 |
+
## Efficient Download Guide
|
| 22 |
+
|
| 23 |
+
To minimize download time and storage usage, please note the function of the files in the repository:
|
| 24 |
+
|
| 25 |
+
**For Inference**: You only need to download config.json and model.safetensors.
|
| 26 |
+
|
| 27 |
+
**For Continued Training**: The file training_state.pt contains optimizer states specifically for resuming training. If you only intend to use the model for inference, you can skip downloading this file.
|
| 28 |
+
|
| 29 |
+
|
| 30 |
## Performance
|
| 31 |
|
| 32 |
### Speculative Sampling Efficiency
|