Hugging Face's logo

Minibase
/
DeId-Small

GGUF
English
text-deidentification
privacy
pii-removal
text2text-generation
medical
legal
hr
llama
minibase
small-model
2048-context
Eval Results
Model card Files
xet
Community
Minibase commited on
Commit
40919d8
·
verified ·
1 Parent(s): f5ad16e

Upload benchmarks.txt with huggingface_hub

Browse files
Files changed (1) hide show
  1. benchmarks.txt +5 -5
benchmarks.txt CHANGED
@@ -2,16 +2,16 @@
2
  **Model:** Minibase-DeId-Small
3
  **Dataset:** Personal_De-identifier_Benchmark_SFT.jsonl
4
  **Sample Size:** 100
5
- **Date:** 2025-09-25T12:38:54.363196
6
 
7
  ## Overall Performance
8
 
9
  | Metric | Score | Description |
10
  |--------|-------|-------------|
11
  | PII Detection Rate | 1.000 | How well personal identifiers are detected |
12
- | Completeness Score | 0.670 | Percentage of texts fully de-identified |
13
- | Semantic Preservation | 0.109 | How well meaning is preserved |
14
- | Average Latency | 483.7ms | Response time performance |
15
 
16
  ## Key Improvements
17
 
@@ -36,6 +36,6 @@
36
  ### Example 3
37
  **Input:** Employee ID: EMP-001-XYZ. Name: John Doe. Salary: $85,000. Email: [email protected]. Marital Stat...
38
  **Expected:** Employee ID: [EMPLOYEE_ID_1]. Name: [NAME_1]. Salary: [SALARY_1]. Email: [EMAIL_1]. Marital Status: ...
39
- **Predicted:** Employee ID: EMP-[BUILDINGNUMBER_1]. Name: [FIRSTNAME_1] Doe. Salary: [CURRENCYSYMBOL_1][AMOUNT_1]. ...
40
  **PII Detection:** 1.000
41
 
 
2
  **Model:** Minibase-DeId-Small
3
  **Dataset:** Personal_De-identifier_Benchmark_SFT.jsonl
4
  **Sample Size:** 100
5
+ **Date:** 2025-09-25T12:48:06.242738
6
 
7
  ## Overall Performance
8
 
9
  | Metric | Score | Description |
10
  |--------|-------|-------------|
11
  | PII Detection Rate | 1.000 | How well personal identifiers are detected |
12
+ | Completeness Score | 0.650 | Percentage of texts fully de-identified |
13
+ | Semantic Preservation | 0.811 | How well meaning is preserved |
14
+ | Average Latency | 477.0ms | Response time performance |
15
 
16
  ## Key Improvements
17
 
 
36
  ### Example 3
37
  **Input:** Employee ID: EMP-001-XYZ. Name: John Doe. Salary: $85,000. Email: [email protected]. Marital Stat...
38
  **Expected:** Employee ID: [EMPLOYEE_ID_1]. Name: [NAME_1]. Salary: [SALARY_1]. Email: [EMAIL_1]. Marital Status: ...
39
+ **Predicted:** Employee ID: EMP-[CREDITCARDCVV_1]. Name: [FIRSTNAME_1] Doe. Salary: [CURRENCYSYMBOL_1][AMOUNT_1]. E...
40
  **PII Detection:** 1.000
41