Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,42 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
# Model Card for Model ID
|
| 6 |
+
|
| 7 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 8 |
+
|
| 9 |
+
The 13B model of "SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens"
|
| 10 |
+
|
| 11 |
+
## Model Details
|
| 12 |
+
|
| 13 |
+
### Model Description
|
| 14 |
+
|
| 15 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 16 |
+
|
| 17 |
+
- **Developed by:** Thundersoft
|
| 18 |
+
- **Language(s) (NLP):** Code
|
| 19 |
+
- **Finetuned from model:** CodeLlama-13B
|
| 20 |
+
|
| 21 |
+
### Model Sources
|
| 22 |
+
|
| 23 |
+
<!-- Provide the basic links for the model. -->
|
| 24 |
+
|
| 25 |
+
- **Repository:** https://github.com/ainergy-ml/SDSAT
|
| 26 |
+
- **Paper:** https://arxiv.org/abs/2403.18647
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
## Evaluation
|
| 30 |
+
|
| 31 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 32 |
+
|
| 33 |
+
### Results
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
### Walltime improvement
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|