liuyashu002
commited on
Commit
·
013a54b
1
Parent(s):
5c11485
readme update
Browse files
README.md
CHANGED
|
@@ -4,7 +4,6 @@ license: apache-2.0
|
|
| 4 |
We open-sourced Flame-Waterfall-7B, a model built by connecting DeepSeek-Coder-7B-Instruct and the SigLIP vision encoder with a 2-layer MLP, and instruction-tuned on the Flame-Code-VLM/Flame-Waterfall-React dataset.
|
| 5 |
This model is released to showcase the value of the synthesized dataset. However, it is not intended for general-purpose tasks. Please use it with caution.
|
| 6 |
|
| 7 |
-
|
| 8 |
### Generation
|
| 9 |
|
| 10 |
The following is the sample code for inference.
|
|
@@ -55,7 +54,7 @@ cont = model.generate(
|
|
| 55 |
input_ids,
|
| 56 |
images=image_tensor,
|
| 57 |
image_sizes=image_sizes,
|
| 58 |
-
modalities=modalities,
|
| 59 |
do_sample=True,
|
| 60 |
num_beams=5,
|
| 61 |
temperature=0.1,
|
|
|
|
| 4 |
We open-sourced Flame-Waterfall-7B, a model built by connecting DeepSeek-Coder-7B-Instruct and the SigLIP vision encoder with a 2-layer MLP, and instruction-tuned on the Flame-Code-VLM/Flame-Waterfall-React dataset.
|
| 5 |
This model is released to showcase the value of the synthesized dataset. However, it is not intended for general-purpose tasks. Please use it with caution.
|
| 6 |
|
|
|
|
| 7 |
### Generation
|
| 8 |
|
| 9 |
The following is the sample code for inference.
|
|
|
|
| 54 |
input_ids,
|
| 55 |
images=image_tensor,
|
| 56 |
image_sizes=image_sizes,
|
| 57 |
+
modalities=modalities, # Added this line with the modalities
|
| 58 |
do_sample=True,
|
| 59 |
num_beams=5,
|
| 60 |
temperature=0.1,
|