Update README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,10 @@
|
|
| 2 |
pipeline_tag: visual-question-answering
|
| 3 |
---
|
| 4 |
|
| 5 |
-
## MiniCPM-Llama3-V 2.5
|
| 6 |
-
|
|
|
|
|
|
|
| 7 |
|
| 8 |
## Usage
|
| 9 |
Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：
|
|
|
|
| 2 |
pipeline_tag: visual-question-answering
|
| 3 |
---
|
| 4 |
|
| 5 |
+
## MiniCPM-Llama3-V 2.5 int4
|
| 6 |
+
This is the int4 quantized version of [MiniCPM-Llama3-V 2.5](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5).
|
| 7 |
+
Running with int4 version would use lower GPU mermory (about 9GB).
|
| 8 |
+
|
| 9 |
|
| 10 |
## Usage
|
| 11 |
Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：
|