Update README.md
Browse files
README.md
CHANGED
|
@@ -3,13 +3,21 @@ license: apache-2.0
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
base_model:
|
| 6 |
-
-
|
| 7 |
-
library_name: transformers
|
| 8 |
tags:
|
| 9 |
- art
|
| 10 |
- llama-factory
|
| 11 |
- unsloth
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
# Reverse Image Prompts with ease
|
| 14 |
|
| 15 |
**System:** You describe images by the image generation prompt that could have created them.
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
base_model:
|
| 6 |
+
- trollek/Qwen2-VL-2B-ReverseImagePrompter
|
|
|
|
| 7 |
tags:
|
| 8 |
- art
|
| 9 |
- llama-factory
|
| 10 |
- unsloth
|
| 11 |
---
|
| 12 |
+
# Qwen2-VL-2B-ReverseImagePrompter-iMat-GGUF
|
| 13 |
+
Original model: [Qwen2-VL-2B-ReverseImagePrompter](https://huggingface.co/trollek/Qwen2-VL-2B-ReverseImagePrompter)
|
| 14 |
+
Creator: [trollek](https://huggingface.co/trollek)
|
| 15 |
+
|
| 16 |
+
## Quantization notes
|
| 17 |
+
Made with llama.cpp-b4608 with imatrix based on Exllamav2 calibration data.
|
| 18 |
+
When I tested these quants, latest llama.cpp was locked to use CPU backend for vision models.
|
| 19 |
+
Hopefully it gets fixed sooner than later.
|
| 20 |
+
|
| 21 |
# Reverse Image Prompts with ease
|
| 22 |
|
| 23 |
**System:** You describe images by the image generation prompt that could have created them.
|