Skip to content

Commit fd0f723

Browse files
author
praveeni
committed
Add full VLM benchmark example to README
1 parent 226efe1 commit fd0f723

File tree

1 file changed

+6
-0
lines changed

1 file changed

+6
-0
lines changed

README.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -280,6 +280,12 @@ lemonade-eval -i Qwen3-4B-VL-FLM load bench --image photo.jpg --image-size 384 -
280280

281281
The `-p` flag controls the text portion of the prompt. Pass an integer for a synthetic prompt of that token length, or a string for a custom prompt. Image tokens are additional and reported by the server in the total input token count.
282282

283+
Full example with all options:
284+
285+
```bash
286+
lemonade-eval -i Qwen3-4B-VL-FLM load bench --image photo.jpg --image-size 1024x800 -p 128 --output-tokens 128 --warmup-iterations 2 --iterations 3
287+
```
288+
283289
## Exporting a Finetuned Model
284290

285291
To prepare your own fine-tuned model for OGA:

0 commit comments

Comments
 (0)