emrulphy commited on
Commit
7517f71
1 Parent(s): ad5ee06

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -6,11 +6,11 @@ metrics:
6
  - accuracy
7
  ---
8
 
9
- # Model Card: POLLCHECK/paligemma
10
 
11
  ## Model Details
12
 
13
- **Model Name:** POLLCHECK/paligemma
14
 
15
  **Model Description:** This is a fine-tuned PaliGemma model for news classification e.g. "biased" or "unbiased". In this particular task, the term 'biased' represents disinformation, propaganda, loaded language, negative associations, generalization, harm, hatred, satire
16
  whereas 'unbiased' represents real news without the spread of misinformation, disinformation, and propaganda. The model can be used to identify potential bias in text and images, which is useful for applications in media analysis, content moderation, and research on bias in written communication.
@@ -50,7 +50,7 @@ from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
50
  device = "cuda:0"
51
  dtype = torch.bfloat16
52
  # Load the fine-tuned model and tokenizer
53
- model_id = "POLLCHECK/paligemma" # path of the model
54
  model = PaliGemmaForConditionalGeneration.from_pretrained(
55
  model_id,
56
  torch_dtype=dtype,
 
6
  - accuracy
7
  ---
8
 
9
+ # Model Card: POLLCHECK/Paligemma-bias-classifier
10
 
11
  ## Model Details
12
 
13
+ **Model Name:** POLLCHECK/Paligemma-bias-classifier
14
 
15
  **Model Description:** This is a fine-tuned PaliGemma model for news classification e.g. "biased" or "unbiased". In this particular task, the term 'biased' represents disinformation, propaganda, loaded language, negative associations, generalization, harm, hatred, satire
16
  whereas 'unbiased' represents real news without the spread of misinformation, disinformation, and propaganda. The model can be used to identify potential bias in text and images, which is useful for applications in media analysis, content moderation, and research on bias in written communication.
 
50
  device = "cuda:0"
51
  dtype = torch.bfloat16
52
  # Load the fine-tuned model and tokenizer
53
+ model_id = "POLLCHECK/Paligemma-bias-classifier" # path of the model
54
  model = PaliGemmaForConditionalGeneration.from_pretrained(
55
  model_id,
56
  torch_dtype=dtype,