Instructions to use Minibase/DeId-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minibase/DeId-Small with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Minibase/DeId-Small",
	filename="model.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Minibase/DeId-Small with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Minibase/DeId-Small
# Run inference directly in the terminal:
llama-cli -hf Minibase/DeId-Small

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Minibase/DeId-Small
# Run inference directly in the terminal:
llama-cli -hf Minibase/DeId-Small

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Minibase/DeId-Small
# Run inference directly in the terminal:
./llama-cli -hf Minibase/DeId-Small

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Minibase/DeId-Small
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Minibase/DeId-Small

Use Docker

docker model run hf.co/Minibase/DeId-Small

LM Studio
Jan
Ollama
How to use Minibase/DeId-Small with Ollama:
```
ollama run hf.co/Minibase/DeId-Small
```

Unsloth Studio new

How to use Minibase/DeId-Small with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Minibase/DeId-Small to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Minibase/DeId-Small to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Minibase/DeId-Small to start chatting

Docker Model Runner
How to use Minibase/DeId-Small with Docker Model Runner:
```
docker model run hf.co/Minibase/DeId-Small
```

Lemonade

How to use Minibase/DeId-Small with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Minibase/DeId-Small

Run and chat with the model

lemonade run user.DeId-Small-{{QUANT_TAG}}

List all available models

lemonade list

Minibase commited on Sep 25, 2025

Commit

4924d32

verified ·

1 Parent(s): 40919d8

Upload benchmark_results.json with huggingface_hub

Browse files

Files changed (1) hide show

benchmark_results.json +25 -25

benchmark_results.json CHANGED Viewed

@@ -1,15 +1,15 @@
 {
   "metadata": {
-    "timestamp": "2025-09-25T12:38:54.363196",
     "model": "Minibase-DeId-Small",
     "dataset": "Personal_De-identifier_Benchmark_SFT.jsonl",
     "sample_size": 100
   },
   "metrics": {
     "pii_detection_rate": 1.0,
-    "completeness_score": 0.67,
-    "semantic_preservation": 0.10869745772803042,
-    "average_latency_ms": 483.6828875541687,
     "successful_requests": 100,
     "total_requests": 100
   },
@@ -22,8 +22,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.14285714285714285,
-        "latency_ms": 465.2400016784668
       }
     },
     {
@@ -33,19 +33,19 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.09090909090909091,
-        "latency_ms": 414.6158695220947
       }
     },
     {
       "input": "Employee ID: EMP-001-XYZ. Name: John Doe. Salary: $85,000. Email: john.doe@example.com. Marital Status: Married. Nationality: Canadian.",
       "expected": "Employee ID: [EMPLOYEE_ID_1]. Name: [NAME_1]. Salary: [SALARY_1]. Email: [EMAIL_1]. Marital Status: [MARITAL_STATUS_1]. Nationality: [NATIONALITY_1].",
-      "predicted": "Employee ID: EMP-[BUILDINGNUMBER_1]. Name: [FIRSTNAME_1] Doe. Salary: [CURRENCYSYMBOL_1][AMOUNT_1]. Email: [EMAIL_1]. Marital Status: Married. Nationality: [STATE_1].",
       "metrics": {
         "pii_detection": 1.0,
         "completeness": false,
-        "semantic_preservation": 0.09090909090909091,
-        "latency_ms": 343.43409538269043
       }
     },
     {
@@ -55,8 +55,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.0,
-        "latency_ms": 543.3461666107178
       }
     },
     {
@@ -66,8 +66,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.1111111111111111,
-        "latency_ms": 286.21578216552734
       }
     },
     {
@@ -77,8 +77,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.2857142857142857,
-        "latency_ms": 293.6849594116211
       }
     },
     {
@@ -88,8 +88,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.125,
-        "latency_ms": 264.0669345855713
       }
     },
     {
@@ -99,8 +99,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.1111111111111111,
-        "latency_ms": 389.96291160583496
       }
     },
     {
@@ -110,8 +110,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": false,
-        "semantic_preservation": 0.0,
-        "latency_ms": 286.5257263183594
       }
     },
     {
@@ -121,8 +121,8 @@
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
-        "semantic_preservation": 0.09090909090909091,
-        "latency_ms": 388.6828422546387
       }
     }
   ]

 {
   "metadata": {
+    "timestamp": "2025-09-25T12:48:06.242738",
     "model": "Minibase-DeId-Small",
     "dataset": "Personal_De-identifier_Benchmark_SFT.jsonl",
     "sample_size": 100
   },
   "metrics": {
     "pii_detection_rate": 1.0,
+    "completeness_score": 0.65,
+    "semantic_preservation": 0.8110479139122438,
+    "average_latency_ms": 477.0322895050049,
     "successful_requests": 100,
     "total_requests": 100
   },
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.7382222222222222,
+        "latency_ms": 499.6819496154785
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.7531262939958592,
+        "latency_ms": 442.65270233154297
       }
     },
     {
       "input": "Employee ID: EMP-001-XYZ. Name: John Doe. Salary: $85,000. Email: john.doe@example.com. Marital Status: Married. Nationality: Canadian.",
       "expected": "Employee ID: [EMPLOYEE_ID_1]. Name: [NAME_1]. Salary: [SALARY_1]. Email: [EMAIL_1]. Marital Status: [MARITAL_STATUS_1]. Nationality: [NATIONALITY_1].",
+      "predicted": "Employee ID: EMP-[CREDITCARDCVV_1]. Name: [FIRSTNAME_1] Doe. Salary: [CURRENCYSYMBOL_1][AMOUNT_1]. Email: [EMAIL_1]. Marital Status: Married. Nationality: [STATE_1].",
       "metrics": {
         "pii_detection": 1.0,
         "completeness": false,
+        "semantic_preservation": 0.8557142857142858,
+        "latency_ms": 359.38310623168945
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.8737037037037036,
+        "latency_ms": 530.4110050201416
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.9,
+        "latency_ms": 294.41308975219727
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.8818181818181818,
+        "latency_ms": 301.6502857208252
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.9846153846153847,
+        "latency_ms": 269.90580558776855
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.9916666666666667,
+        "latency_ms": 399.30129051208496
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": false,
+        "semantic_preservation": 0.8596491228070176,
+        "latency_ms": 292.7100658416748
       }
     },
     {
       "metrics": {
         "pii_detection": 1.0,
         "completeness": true,
+        "semantic_preservation": 0.8733333333333333,
+        "latency_ms": 410.9461307525635
       }
     }
   ]