Commit
·
5aa4eab
1
Parent(s):
f82d9d1
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,11 @@ Please apply megdgmma thinking-systemprompts.txt when using.
|
|
| 31 |
1. I plan to continue improve this model,
|
| 32 |
Please please support me. Bitcoin address : 34ZuzEUfuVfuEE8PiU1DabiwRzAxGw9JM4
|
| 33 |
2. I Uploded model Files.
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
```yaml
|
| 37 |
models:
|
|
|
|
| 31 |
1. I plan to continue improve this model,
|
| 32 |
Please please support me. Bitcoin address : 34ZuzEUfuVfuEE8PiU1DabiwRzAxGw9JM4
|
| 33 |
2. I Uploded model Files.
|
| 34 |
+
3.I adapted the LoRA for MedGemma-27B-it,
|
| 35 |
+
which was released publicly,to megdgmma3-thinking, and found that
|
| 36 |
+
the accuracy of reading medical images improved.
|
| 37 |
+
Therefore, I uploaded the used LoRA (LoRA and Page URL),
|
| 38 |
+
the LoRA-adapted main model, LoRA-adapted GGUF, and its test output as a megdgmma3-thinking-DirectLoRA file.
|
| 39 |
|
| 40 |
```yaml
|
| 41 |
models:
|