Transformers
Safetensors
dflash2
speculative-decoding
draft-model
Mixture of Experts
code
speculators
vllm
Instructions to use DaoCloud/KAT-Coder-V2.5-Dev-DFlash2-2.6B-A0.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DaoCloud/KAT-Coder-V2.5-Dev-DFlash2-2.6B-A0.3B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DaoCloud/KAT-Coder-V2.5-Dev-DFlash2-2.6B-A0.3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -62,6 +62,7 @@ This release explores the same direction with a DFlash2 drafter: approximately 2
|
|
| 62 |
| SpeedBench / stem | 80 | 2.3774 | 3.0061 |
|
| 63 |
| SpeedBench / summarization | 80 | 3.0177 | 2.6967 |
|
| 64 |
| SpeedBench / writing | 80 | 2.2223 | 2.3711 |
|
|
|
|
| 65 |
Accepted length is calculated from the raw server counters:
|
| 66 |
|
| 67 |
```text
|
|
|
|
| 62 |
| SpeedBench / stem | 80 | 2.3774 | 3.0061 |
|
| 63 |
| SpeedBench / summarization | 80 | 3.0177 | 2.6967 |
|
| 64 |
| SpeedBench / writing | 80 | 2.2223 | 2.3711 |
|
| 65 |
+
|
| 66 |
Accepted length is calculated from the raw server counters:
|
| 67 |
|
| 68 |
```text
|