Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,9 @@ This model [sealad886/gpt-oss-20b-MLX-native](https://huggingface.co/sealad886/g
|
|
| 14 |
converted to MLX format from [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b)
|
| 15 |
using mlx-lm version **0.26.3**.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
## Use with mlx
|
| 18 |
|
| 19 |
```bash
|
|
|
|
| 14 |
converted to MLX format from [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b)
|
| 15 |
using mlx-lm version **0.26.3**.
|
| 16 |
|
| 17 |
+
Note: command for conversion: `mlx_lm.convert --hf-repo openai/gpt-oss-20b ... -q --q-bits 4`
|
| 18 |
+
The version without doing an added 4-bit quant was in a 16-bit format (either bfloat16 or float16, I assume...I didn't check).
|
| 19 |
+
|
| 20 |
## Use with mlx
|
| 21 |
|
| 22 |
```bash
|