Update README.md
Browse files
README.md
CHANGED
|
@@ -50,7 +50,7 @@ python scripts/generate.py --mlx mage-vl-mlx --tokenizer-src mage-vl-mlx \
|
|
| 50 |
|
| 51 |
4-bit is recommended for 16GB; 8-bit gives richer output if you have RAM.
|
| 52 |
|
| 53 |
-
## Validation
|
| 54 |
|
| 55 |
- **Image preprocessing**: bit-exact vs the HF `Qwen2VLImageProcessor` (max_abs_diff 0.0).
|
| 56 |
- **Vision tower**: numerically matches the reference weights end-to-end
|
|
|
|
| 50 |
|
| 51 |
4-bit is recommended for 16GB; 8-bit gives richer output if you have RAM.
|
| 52 |
|
| 53 |
+
## Validation
|
| 54 |
|
| 55 |
- **Image preprocessing**: bit-exact vs the HF `Qwen2VLImageProcessor` (max_abs_diff 0.0).
|
| 56 |
- **Vision tower**: numerically matches the reference weights end-to-end
|