Instructions to use CMB-AI-LAB/lagkv_cache with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CMB-AI-LAB/lagkv_cache with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CMB-AI-LAB/lagkv_cache", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
custom_generate/generate.py
CHANGED
|
@@ -13,7 +13,7 @@
|
|
| 13 |
# limitations under the License.
|
| 14 |
|
| 15 |
import torch
|
| 16 |
-
from transformers
|
| 17 |
from typing import Any, Dict, List, Optional, Tuple
|
| 18 |
|
| 19 |
|
|
|
|
| 13 |
# limitations under the License.
|
| 14 |
|
| 15 |
import torch
|
| 16 |
+
from transformers import DynamicCache, GenerationConfig
|
| 17 |
from typing import Any, Dict, List, Optional, Tuple
|
| 18 |
|
| 19 |
|