Update README.md
Browse files
README.md
CHANGED
|
@@ -60,70 +60,7 @@ The fine-tuning data used for BioChat is derived from the [ChatDoctor-5k](https:
|
|
| 60 |
|
| 61 |
To determine the best model for fine-tuning, I used *perplexity* as a metric to evaluate performance and select the most optimal version. By leveraging the model's capabilities, I aim to evaluate its behavior and responses using tools like the *Word Embedding Association Test (WEAT)*. It is important to emphasize that its text generation features are intended solely for research purposes and are not yet suitable for production use. By releasing this model, we aim to drive advancements in biomedical NLP applications and contribute to best practices for the responsible development of domain-specific language models. Ensuring reliability, fairness, accuracy, and explainability remains a top priority for us.
|
| 62 |
|
| 63 |
-
### Testing Data, Factors & Metrics
|
| 64 |
|
| 65 |
-
#### Testing Data
|
| 66 |
-
|
| 67 |
-
<!-- This should link to a Dataset Card if possible. -->
|
| 68 |
-
|
| 69 |
-
[More Information Needed]
|
| 70 |
-
|
| 71 |
-
#### Factors
|
| 72 |
-
|
| 73 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 74 |
-
|
| 75 |
-
[More Information Needed]
|
| 76 |
-
|
| 77 |
-
#### Metrics
|
| 78 |
-
|
| 79 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 80 |
-
|
| 81 |
-
[More Information Needed]
|
| 82 |
-
|
| 83 |
-
### Results
|
| 84 |
-
|
| 85 |
-
[More Information Needed]
|
| 86 |
-
|
| 87 |
-
#### Summary
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
## Model Examination [optional]
|
| 92 |
-
|
| 93 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 94 |
-
|
| 95 |
-
[More Information Needed]
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
## Citation [optional]
|
| 99 |
-
|
| 100 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 101 |
-
|
| 102 |
-
**BibTeX:**
|
| 103 |
-
|
| 104 |
-
[More Information Needed]
|
| 105 |
-
|
| 106 |
-
**APA:**
|
| 107 |
-
|
| 108 |
-
[More Information Needed]
|
| 109 |
-
|
| 110 |
-
## Glossary [optional]
|
| 111 |
-
|
| 112 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 113 |
-
|
| 114 |
-
[More Information Needed]
|
| 115 |
-
|
| 116 |
-
## More Information [optional]
|
| 117 |
-
|
| 118 |
-
[More Information Needed]
|
| 119 |
-
|
| 120 |
-
## Model Card Authors [optional]
|
| 121 |
-
|
| 122 |
-
[More Information Needed]
|
| 123 |
-
|
| 124 |
-
## Model Card Contact
|
| 125 |
-
|
| 126 |
-
[More Information Needed]
|
| 127 |
### Framework versions
|
| 128 |
|
| 129 |
- PEFT 0.11.1
|
|
|
|
| 60 |
|
| 61 |
To determine the best model for fine-tuning, I used *perplexity* as a metric to evaluate performance and select the most optimal version. By leveraging the model's capabilities, I aim to evaluate its behavior and responses using tools like the *Word Embedding Association Test (WEAT)*. It is important to emphasize that its text generation features are intended solely for research purposes and are not yet suitable for production use. By releasing this model, we aim to drive advancements in biomedical NLP applications and contribute to best practices for the responsible development of domain-specific language models. Ensuring reliability, fairness, accuracy, and explainability remains a top priority for us.
|
| 62 |
|
|
|
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
### Framework versions
|
| 65 |
|
| 66 |
- PEFT 0.11.1
|