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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Minibase/NER-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/NER-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/NER-Small
# Run inference directly in the terminal:
llama-cli -hf Minibase/NER-Small

Install from WinGet (Windows)

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

Use Docker

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

LM Studio
Jan

vLLM

How to use Minibase/NER-Small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minibase/NER-Small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Minibase/NER-Small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

Ollama
How to use Minibase/NER-Small with Ollama:
```
ollama run hf.co/Minibase/NER-Small
```

Unsloth Studio new

How to use Minibase/NER-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/NER-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/NER-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/NER-Small to start chatting

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

Lemonade

How to use Minibase/NER-Small with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Minibase commited on Oct 7, 2025

Commit

d7c73a3

verified ·

1 Parent(s): 88401ca

Upload benchmark_config.yaml with huggingface_hub

Browse files

Files changed (1) hide show

benchmark_config.yaml +56 -0

benchmark_config.yaml ADDED Viewed

	@@ -0,0 +1,56 @@

+model:
+  base_url: "http://127.0.0.1:8000"
+  max_tokens: 512
+  temperature: 0.1
+  timeout: 30
+datasets:
+  benchmark_dataset:
+    file_path: "ner_benchmark_dataset.jsonl"
+    sample_size: 100  # Use first 100 examples for quick benchmarking
+    instruction_field: "instruction"
+    input_field: "input"
+    expected_output_field: "response"
+metrics:
+  # Primary metrics for HuggingFace
+  entity_recognition:
+    name: "Entity Recognition F1 Score"
+    description: "F1 score for named entity recognition accuracy"
+    type: "f1"
+  precision:
+    name: "Precision Score"
+    description: "Precision for entity recognition"
+    type: "precision"
+  recall:
+    name: "Recall Score"
+    description: "Recall for entity recognition"
+    type: "recall"
+  latency:
+    name: "Average Latency"
+    description: "Average response time in milliseconds"
+    type: "latency"
+  # Entity type specific performance
+  entity_types:
+    person:
+      name: "Person Entity Recognition"
+      keywords: ["PERSON", "person", "Person"]
+    organization:
+      name: "Organization Entity Recognition"
+      keywords: ["ORG", "organization", "Organization"]
+    location:
+      name: "Location Entity Recognition"
+      keywords: ["LOC", "location", "Location"]
+    miscellaneous:
+      name: "Miscellaneous Entity Recognition"
+      keywords: ["MISC", "miscellaneous", "Miscellaneous"]
+output:
+  results_file: "benchmarks.txt"
+  detailed_results_file: "benchmark_results.json"
+  include_examples: true
+  max_examples: 10