Visual Question Answering
Transformers
Safetensors
English
vlm
text-generation
image-captioning
Inference Endpoints
kimihailv commited on
Commit
00cf28a
1 Parent(s): 560c6e4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -24,6 +24,15 @@ The model was pre-trained on: MSCOCO, SBU Captions, Visual Genome, VQAv2, GQA an
24
  pip install uform
25
  ```
26
 
 
 
 
 
 
 
 
 
 
27
  ```python
28
  from uform.gen_model import VLMForCausalLM, VLMProcessor
29
 
 
24
  pip install uform
25
  ```
26
 
27
+ For the CLI demo run the following:
28
+
29
+ ```bash
30
+ uform-chat --model unum-cloud/uform-gen-chat --image_path=zebra.jpg
31
+ uform-chat --model unum-cloud/uform-gen-chat --image_path=zebra.jpg --device="cuda:0" --fp16
32
+ ```
33
+
34
+ Or if you want to use the model in your code:
35
+
36
  ```python
37
  from uform.gen_model import VLMForCausalLM, VLMProcessor
38