averbitsky commited on
Commit
a1944d5
·
verified ·
1 Parent(s): 8d217a3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -4
README.md CHANGED
@@ -32,7 +32,6 @@ tags:
32
  ## Model Details
33
 
34
  ### Model Description
35
-
36
  `netrias/cancer_harmonization_gpt2large` is a fine-tuned GPT2-Large model for harmonizing cancer-related biomedical terms. It converts variant input terms, such as synonyms, abbreviations, misspellings, and rephrasings, into standardized terms for consistent metadata curation.
37
 
38
  - **Developed by:** [Netrias, LLC](https://www.netrias.com/)
@@ -42,7 +41,6 @@ tags:
42
  - **Fine-tuned from model:** [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large)
43
 
44
  ### Model Sources
45
-
46
  - **Repository:** [netrias/cancer_harmonization_gpt2large](https://huggingface.co/netrias/cancer_harmonization_gpt2large)
47
  - **Paper:** [Metadata Harmonization from Biological Datasets with Language Models](https://doi.org/10.1101/2025.01.15.633281)
48
 
@@ -64,7 +62,6 @@ This model was trained on a narrow domain, limiting its applicability to other b
64
  Limit use to the supported domain, and validate outputs before applying them in downstream applications.
65
 
66
  ## How to Get Started with the Model
67
-
68
  Prompt the model using a structured sentence of the form: `The standardized form of "your input term" is "`. It returns the most likely standardized term, followed by a closing quote. The example below uses Hugging Face's `pipeline` to generate the top 5 completions using beam search:
69
 
70
  ```python
@@ -151,7 +148,6 @@ Results are disaggregated by dictionary inclusion: whether the gold standard app
151
  High performance on the validation and ID test sets indicates effective learning of known representations. Lower performance on OOD terms suggests reduced generalization to unseen standards and highlights the importance of human review for unfamiliar inputs.
152
 
153
  ## Environmental Impact
154
-
155
  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
156
 
157
  - **Hardware Type:** NVIDIA A10G
 
32
  ## Model Details
33
 
34
  ### Model Description
 
35
  `netrias/cancer_harmonization_gpt2large` is a fine-tuned GPT2-Large model for harmonizing cancer-related biomedical terms. It converts variant input terms, such as synonyms, abbreviations, misspellings, and rephrasings, into standardized terms for consistent metadata curation.
36
 
37
  - **Developed by:** [Netrias, LLC](https://www.netrias.com/)
 
41
  - **Fine-tuned from model:** [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large)
42
 
43
  ### Model Sources
 
44
  - **Repository:** [netrias/cancer_harmonization_gpt2large](https://huggingface.co/netrias/cancer_harmonization_gpt2large)
45
  - **Paper:** [Metadata Harmonization from Biological Datasets with Language Models](https://doi.org/10.1101/2025.01.15.633281)
46
 
 
62
  Limit use to the supported domain, and validate outputs before applying them in downstream applications.
63
 
64
  ## How to Get Started with the Model
 
65
  Prompt the model using a structured sentence of the form: `The standardized form of "your input term" is "`. It returns the most likely standardized term, followed by a closing quote. The example below uses Hugging Face's `pipeline` to generate the top 5 completions using beam search:
66
 
67
  ```python
 
148
  High performance on the validation and ID test sets indicates effective learning of known representations. Lower performance on OOD terms suggests reduced generalization to unseen standards and highlights the importance of human review for unfamiliar inputs.
149
 
150
  ## Environmental Impact
 
151
  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
152
 
153
  - **Hardware Type:** NVIDIA A10G