Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -11,8 +11,6 @@ tags:
|
|
| 11 |
- text-generation
|
| 12 |
---
|
| 13 |
|
| 14 |
-
> Previously published as `harpertoken/harpertoken-apple-m1-model`. The old identifier still redirects here.
|
| 15 |
-
|
| 16 |
# tiny
|
| 17 |
|
| 18 |
A four-bit quantised conversion of [`mlx-community/SmolLM-135M-Instruct-4bit`](https://huggingface.co/mlx-community/SmolLM-135M-Instruct-4bit), produced with `mlx-lm` 0.30.4 and intended for Apple Silicon. The architecture is a Llama variant — thirty layers, 576 hidden dimensions, nine attention heads, three key-value heads, 49152-token vocabulary — with group-size 64 four-bit weights, occupying about 76 MB.
|
|
|
|
| 11 |
- text-generation
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
| 14 |
# tiny
|
| 15 |
|
| 16 |
A four-bit quantised conversion of [`mlx-community/SmolLM-135M-Instruct-4bit`](https://huggingface.co/mlx-community/SmolLM-135M-Instruct-4bit), produced with `mlx-lm` 0.30.4 and intended for Apple Silicon. The architecture is a Llama variant — thirty layers, 576 hidden dimensions, nine attention heads, three key-value heads, 49152-token vocabulary — with group-size 64 four-bit weights, occupying about 76 MB.
|