Instructions to use cstr/xlmr-ner-hrl-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/xlmr-ner-hrl-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cstr/xlmr-ner-hrl-GGUF",
	filename="xlmr-ner-hrl-f32.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 cstr/xlmr-ner-hrl-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/xlmr-ner-hrl-GGUF:F32
# Run inference directly in the terminal:
llama-cli -hf cstr/xlmr-ner-hrl-GGUF:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/xlmr-ner-hrl-GGUF:F32
# Run inference directly in the terminal:
llama-cli -hf cstr/xlmr-ner-hrl-GGUF:F32

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 cstr/xlmr-ner-hrl-GGUF:F32
# Run inference directly in the terminal:
./llama-cli -hf cstr/xlmr-ner-hrl-GGUF:F32

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 cstr/xlmr-ner-hrl-GGUF:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cstr/xlmr-ner-hrl-GGUF:F32

Use Docker

docker model run hf.co/cstr/xlmr-ner-hrl-GGUF:F32

LM Studio
Jan
Ollama
How to use cstr/xlmr-ner-hrl-GGUF with Ollama:
```
ollama run hf.co/cstr/xlmr-ner-hrl-GGUF:F32
```

Unsloth Studio

How to use cstr/xlmr-ner-hrl-GGUF 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 cstr/xlmr-ner-hrl-GGUF 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 cstr/xlmr-ner-hrl-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cstr/xlmr-ner-hrl-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use cstr/xlmr-ner-hrl-GGUF with Docker Model Runner:
```
docker model run hf.co/cstr/xlmr-ner-hrl-GGUF:F32
```

Lemonade

How to use cstr/xlmr-ner-hrl-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cstr/xlmr-ner-hrl-GGUF:F32

Run and chat with the model

lemonade run user.xlmr-ner-hrl-GGUF-F32

List all available models

lemonade list

XLM-R NER HRL — GGUF

GGUF conversion of Davlan/xlm-roberta-base-ner-hrl for CrispEmbed.

Multilingual NER (10 high-resource languages). XLM-RoBERTa-base (278M params), 9 IOB labels: O, B-DATE, I-DATE, B-PER, I-PER, B-ORG, I-ORG, B-LOC, I-LOC.

File	Format	Size
xlmr-ner-hrl-f32.gguf	F32	1064 MB
xlmr-ner-hrl-q8_0.gguf	Q8_0	281 MB
xlmr-ner-hrl-q4_k.gguf	Q4_K	241 MB

Auto-detected as BERT NER backend by CrispEmbed (same API as bert-base-NER).

Note: Original model states Academic Free License v3.0, but was trained on datasets like conll 2003.

Downloads last month: 73

GGUF

Model size

0.3B params

Architecture

xlmr

Hardware compatibility

8-bit

32-bit

Model tree for cstr/xlmr-ner-hrl-GGUF

Base model

Davlan/xlm-roberta-base-ner-hrl

Quantized

(4)

this model