Instructions to use crumb/gzip-openhermes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use crumb/gzip-openhermes with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("crumb/gzip-openhermes", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,9 +12,11 @@ It's so funny that the huggingface hub lets you do this
|
|
| 12 |
| model | parameters | embedding dimensions |
|
| 13 |
| --- | --- | --- |
|
| 14 |
| meta-llama/Llama-2-70b-hf | 70b | 8192 |
|
| 15 |
-
| crumb/
|
| 16 |
|
| 17 |
-
the huggingface pretrained model saving api requires at least one parameter, which is set to "1" in this model.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
pruning:
|
| 20 |
```python
|
|
|
|
| 12 |
| model | parameters | embedding dimensions |
|
| 13 |
| --- | --- | --- |
|
| 14 |
| meta-llama/Llama-2-70b-hf | 70b | 8192 |
|
| 15 |
+
| crumb/gzip-openhermes | 1* | 242,831 |
|
| 16 |
|
| 17 |
+
*the huggingface pretrained model saving api requires at least one parameter, which is set to "1" in this model.
|
| 18 |
+
|
| 19 |
+
multiprocessing is suuuper weird so make sure you dont have the variables "p" or "calculate_ncd_row" in your code anywhere..
|
| 20 |
|
| 21 |
pruning:
|
| 22 |
```python
|