Instructions to use apple/CLaRa-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/CLaRa-7B-Instruct with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("apple/CLaRa-7B-Instruct", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update compression-16/config.json
Browse files
compression-16/config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"model_type": "CLaRa",
|
| 31 |
"optimize_mem_tokens": true,
|
| 32 |
"pad_token_id": 2,
|
| 33 |
-
"pure_inference":
|
| 34 |
"quantization": "no",
|
| 35 |
"sep": true,
|
| 36 |
"stage2_retrieval_top_n": 1,
|
|
|
|
| 30 |
"model_type": "CLaRa",
|
| 31 |
"optimize_mem_tokens": true,
|
| 32 |
"pad_token_id": 2,
|
| 33 |
+
"pure_inference": true,
|
| 34 |
"quantization": "no",
|
| 35 |
"sep": true,
|
| 36 |
"stage2_retrieval_top_n": 1,
|