StarCycle commited on
Commit
0c69c7d
1 Parent(s): 69c10d4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -11,7 +11,6 @@ llava-dinov2-internlm2-7b-v1 is a LLaVA model fine-tuned from [InternLM2-Chat-7B
11
  I did not carefully tune the training hyperparameters but the model still show capability to solve some tasks. It shows that a visual encoder can be integrated with an LLM, even when the encoder is not aligned with natural language with contrastive learning like CLIP.
12
 
13
  ## Example
14
-
15
  ![5bb2f23dd595d389e6a9a0aadebd87c.png](https://cdn-uploads.huggingface.co/production/uploads/642a298ae5f33939cf3ee600/iOFZOwLGfEByCQ_2EkR7y.png)
16
  Explain the photo in English:
17
  ![eeb555092886be02e8e6215d0fdb229.png](https://cdn-uploads.huggingface.co/production/uploads/642a298ae5f33939cf3ee600/CASHz1oxgowVS3n5e4LUq.png)
@@ -77,9 +76,13 @@ You just need
77
  ```
78
  pip install protobuf
79
  ```
 
 
 
 
 
80
 
81
  ## Data prepration
82
-
83
  1. File structure
84
 
85
  ```
 
11
  I did not carefully tune the training hyperparameters but the model still show capability to solve some tasks. It shows that a visual encoder can be integrated with an LLM, even when the encoder is not aligned with natural language with contrastive learning like CLIP.
12
 
13
  ## Example
 
14
  ![5bb2f23dd595d389e6a9a0aadebd87c.png](https://cdn-uploads.huggingface.co/production/uploads/642a298ae5f33939cf3ee600/iOFZOwLGfEByCQ_2EkR7y.png)
15
  Explain the photo in English:
16
  ![eeb555092886be02e8e6215d0fdb229.png](https://cdn-uploads.huggingface.co/production/uploads/642a298ae5f33939cf3ee600/CASHz1oxgowVS3n5e4LUq.png)
 
76
  ```
77
  pip install protobuf
78
  ```
79
+ 4.
80
+ To use tensorboard to visualize the training loss curve:
81
+ ```
82
+ pip install future tensorboard
83
+ ```
84
 
85
  ## Data prepration
 
86
  1. File structure
87
 
88
  ```