Instructions to use aoxo/kevin-token-compressor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aoxo/kevin-token-compressor with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Meta-Llama-3.1-8B-bnb-4bit") model = PeftModel.from_pretrained(base_model, "aoxo/kevin-token-compressor") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,9 +20,9 @@ tags:
|
|
| 20 |
pipeline_tag: text-generation
|
| 21 |
---
|
| 22 |
|
| 23 |
-
#
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
## Model Details
|
| 28 |
|
|
|
|
| 20 |
pipeline_tag: text-generation
|
| 21 |
---
|
| 22 |
|
| 23 |
+
# Kevin - A Token Compressor for Long-Range Dependency Conversations
|
| 24 |
|
| 25 |
+

|
| 26 |
|
| 27 |
## Model Details
|
| 28 |
|