float16 (#1)
Browse files- float16 (72070040a93c3c3719bc49ae1a01bae3b721ad9d)
README.md
CHANGED
|
@@ -13,5 +13,7 @@ tags:
|
|
| 13 |
|
| 14 |
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, in `npz` format suitable for use in Apple's MLX framework.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
Please, refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b-chat/tree/main) for details on Llama 2.
|
| 17 |
|
|
|
|
| 13 |
|
| 14 |
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, in `npz` format suitable for use in Apple's MLX framework.
|
| 15 |
|
| 16 |
+
Weights have been converted to `float16` from the original `bfloat16` type, because `numpy` is not compatible with `bfloat16` out of the box.
|
| 17 |
+
|
| 18 |
Please, refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b-chat/tree/main) for details on Llama 2.
|
| 19 |
|