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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Minibase/NER-Standard with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Minibase/NER-Standard
# Run inference directly in the terminal:
llama cli -hf Minibase/NER-Standard

Install from WinGet (Windows)

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

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-Standard
# Run inference directly in the terminal:
./llama-cli -hf Minibase/NER-Standard

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-Standard
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Minibase/NER-Standard

Use Docker

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

LM Studio
Jan

vLLM

How to use Minibase/NER-Standard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minibase/NER-Standard"
# 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-Standard",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

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

Unsloth Studio

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

Atomic Chat new
Docker Model Runner
How to use Minibase/NER-Standard with Docker Model Runner:
```
docker model run hf.co/Minibase/NER-Standard
```

Lemonade

How to use Minibase/NER-Standard with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Minibase commited on Oct 7, 2025

Commit

4e3daed

verified ·

1 Parent(s): 74af1e5

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +3 -76

config.json CHANGED Viewed

@@ -1,76 +1,3 @@
-{
-  "_name_or_path": "NER-Standard",
-  "architectures": ["LlamaForCausalLM"],
-  "vocab_size": 49152,
-  "context_length": 2048,
-  "hidden_size": 576,
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "intermediate_size": 1536,
-  "quantization_config": {
-    "quant_method": "gguf",
-    "quantization_type": "Q8_0",
-    "quantization_bits": 8,
-    "compression_ratio": 0.5,
-    "quantization_version": "2",
-    "quantization_fidelity": "high",
-    "quantization_format": "GGUF",
-    "quantization_description": "8-bit quantization with optimized weights for high fidelity"
-  },
-  "file_size": 143025408,
-  "file_size_mb": 143,
-  "gguf_file": "model.gguf",
-  "model_family": "llama",
-  "model_version": "1.0.0",
-  "hardware_requirements": {
-    "minimum_ram": "8GB",
-    "recommended_ram": "16GB",
-    "cpu_compatibility": "Any modern CPU",
-    "gpu_compatibility": {
-      "nvidia": "Any CUDA-compatible GPU",
-      "amd": "Any ROCm-compatible GPU",
-      "apple_silicon": "M1/M2/M3/M4 chips with Metal"
-    },
-    "os_compatibility": ["linux", "macos", "windows"],
-    "recommended_hardware": "Apple Silicon M2/M3/M4, Intel i7/i9, or NVIDIA RTX 30-series",
-    "memory_usage_estimate": "~2GB during inference",
-    "storage_requirements": "150MB free space"
-  },
-  "performance_metrics": {
-    "ner_f1_score": 0.951,
-    "precision": 0.915,
-    "recall": 1.000,
-    "entity_types_supported": ["PERSON", "ORG", "LOC", "MISC"],
-    "latency_ms": 323.3,
-    "throughput_requests_per_second": 3.1,
-    "benchmark_dataset": "NER Benchmark Dataset",
-    "benchmark_samples": 100,
-    "evaluation_date": "2025-10-07"
-  },
-  "model_creator": "Minibase AI",
-  "model_url": "https://minibase.ai",
-  "discord_url": "https://discord.com/invite/BrJn4D2Guh",
-    "repository_url": "https://github.com/minibase-ai/ner-standard",
-    "paper_url": "https://minibase.ai/research/ner-standard",
-  "license": "apache-2.0",
-  "tags": [
-    "text-generation",
-    "named-entity-recognition",
-    "ner",
-    "nlp",
-    "information-extraction",
-    "person",
-    "organization",
-    "location",
-    "miscellaneous",
-    "llama",
-    "gguf",
-    "quantized",
-    "cpu-inference",
-    "apple-silicon",
-    "minibase",
-    "standard-model",
-    "2048-context",
-    "q8_0"
-  ]
-}

+version https://git-lfs.github.com/spec/v1
+oid sha256:904a63de9bd60dc95f16a0f5518acf7c8249782849c95724962a3af937dac700
+size 2258