Instructions to use antflydb/gliner2-base-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use antflydb/gliner2-base-v1 with GLiNER2:

from gliner2 import GLiNER2

model = GLiNER2.from_pretrained("antflydb/gliner2-base-v1")

# Extract entities
text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday."
result = extractor.extract_entities(text, ["company", "person", "product", "location"])

print(result)

llama-cpp-python

How to use antflydb/gliner2-base-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="antflydb/gliner2-base-v1",
	filename="gliner2-encoder.Q4_K.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 antflydb/gliner2-base-v1 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 antflydb/gliner2-base-v1
# Run inference directly in the terminal:
llama cli -hf antflydb/gliner2-base-v1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf antflydb/gliner2-base-v1
# Run inference directly in the terminal:
llama cli -hf antflydb/gliner2-base-v1

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 antflydb/gliner2-base-v1
# Run inference directly in the terminal:
./llama-cli -hf antflydb/gliner2-base-v1

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 antflydb/gliner2-base-v1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf antflydb/gliner2-base-v1

Use Docker

docker model run hf.co/antflydb/gliner2-base-v1

LM Studio
Jan
Ollama
How to use antflydb/gliner2-base-v1 with Ollama:
```
ollama run hf.co/antflydb/gliner2-base-v1
```

Unsloth Studio

How to use antflydb/gliner2-base-v1 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 antflydb/gliner2-base-v1 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 antflydb/gliner2-base-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for antflydb/gliner2-base-v1 to start chatting

Atomic Chat new
Docker Model Runner
How to use antflydb/gliner2-base-v1 with Docker Model Runner:
```
docker model run hf.co/antflydb/gliner2-base-v1
```

Lemonade

How to use antflydb/gliner2-base-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull antflydb/gliner2-base-v1

Run and chat with the model

lemonade run user.gliner2-base-v1-{{QUANT_TAG}}

List all available models

lemonade list

antflydb/gliner2-base-v1

Antfly GLiNER2 base bundle with a ClipClap-style flat variants layout.

The gguf-Q4_K variant is a split native bundle:

gliner2-encoder.Q4_K.gguf
gliner2-head.Q4_K.gguf

The repo also includes:

model.onnx, copied from lion-ai/gliner2-base-v1-onnx
model.safetensors, copied from fastino/gliner2-base-v1
tokenizer and GLiNER2 sidecars from the upstream/base bundle

Antfly Inference reads antfly_inference_variants.json and resolves complete encoder/head pairs as gliner2_split_bundle/v1 at load time.

How to Use with Antfly Inference

antfly inference pull antflydb/gliner2-base-v1:gguf:Q4_K
antfly inference run

Advertised Antfly Inference tasks:

recognize
extract
classify

Relation extraction is advertised as a capability and is driven through the extraction schema.

Downloads last month: 197

Safetensors

Model size

0.2B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for antflydb/gliner2-base-v1

Base model

fastino/gliner2-base-v1

Quantized

(5)

this model