FabioS08 commited on
Commit
e2083e9
1 Parent(s): 7647d27

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -6,7 +6,7 @@ pipeline_tag: question-answering
6
  ---
7
  # Model Description
8
  This is a fine-tuned version of the Minerva model, trained on the [Medical Meadow Flashcard Dataset](https://huggingface.co/datasets/medalpaca/medical_meadow_medical_flashcards) for question answering. The model was developed by the Sapienza NLP Team in collaboration with Future Artificial Intelligence Research (FAIR) and CINECA; specifically, I used the version with 350 million parameters due to computational limits, though versions with 1 billion and 3 billion parameters also exist. For more details, please refer to their repositories: [Sapienza NLP on Hugging Face](https://huggingface.co/sapienzanlp) and [Minerva LLMs](https://nlp.uniroma1.it/minerva/).
9
-
10
  # Issues and possible Solutions
11
  - In the original fine-tuned version, my model tended to generate answers that continued unnecessarily, leading to repeated sentences and a degradation in quality over time. Parameters like '*max_length*' or '*max_new_tokens*' were ineffective as they merely stopped the generation at a specified point without properly concluding the sentence. To address this issue, I redefined the stopping criteria to terminate the generation at the first period ('.'), as demonstrated in the code below:
12
  - ```python
@@ -32,6 +32,7 @@ This is a fine-tuned version of the Minerva model, trained on the [Medical Meado
32
  inputText = tokenizer.decode(inputEncoding.input_ids[0], skip_special_tokens = True)
33
  answer = outputText[len(inputText):].strip()
34
  ```
 
35
 
36
  # Use Example
37
 
@@ -59,6 +60,7 @@ This is a fine-tuned version of the Minerva model, trained on the [Medical Meado
59
  # Generated Answer: Wernicke encephalopathy is caused by a defect in the Wern-Herxheimer reaction, which leads to an accumulation of acid and alkaline phosphatase activity.
60
  # Effective Answer: The underlying pathophysiologic cause of Wernicke encephalopathy is thiamine (B1) deficiency.
61
  ```
 
62
 
63
  # Training Information
64
  The model was fine-tuned for 3 epochs using the parameters specified in its original repository:
 
6
  ---
7
  # Model Description
8
  This is a fine-tuned version of the Minerva model, trained on the [Medical Meadow Flashcard Dataset](https://huggingface.co/datasets/medalpaca/medical_meadow_medical_flashcards) for question answering. The model was developed by the Sapienza NLP Team in collaboration with Future Artificial Intelligence Research (FAIR) and CINECA; specifically, I used the version with 350 million parameters due to computational limits, though versions with 1 billion and 3 billion parameters also exist. For more details, please refer to their repositories: [Sapienza NLP on Hugging Face](https://huggingface.co/sapienzanlp) and [Minerva LLMs](https://nlp.uniroma1.it/minerva/).
9
+ <br>
10
  # Issues and possible Solutions
11
  - In the original fine-tuned version, my model tended to generate answers that continued unnecessarily, leading to repeated sentences and a degradation in quality over time. Parameters like '*max_length*' or '*max_new_tokens*' were ineffective as they merely stopped the generation at a specified point without properly concluding the sentence. To address this issue, I redefined the stopping criteria to terminate the generation at the first period ('.'), as demonstrated in the code below:
12
  - ```python
 
32
  inputText = tokenizer.decode(inputEncoding.input_ids[0], skip_special_tokens = True)
33
  answer = outputText[len(inputText):].strip()
34
  ```
35
+ <br>
36
 
37
  # Use Example
38
 
 
60
  # Generated Answer: Wernicke encephalopathy is caused by a defect in the Wern-Herxheimer reaction, which leads to an accumulation of acid and alkaline phosphatase activity.
61
  # Effective Answer: The underlying pathophysiologic cause of Wernicke encephalopathy is thiamine (B1) deficiency.
62
  ```
63
+ <br>
64
 
65
  # Training Information
66
  The model was fine-tuned for 3 epochs using the parameters specified in its original repository: