Instructions to use llmware/bling-answer-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/bling-answer-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/bling-answer-tool", dtype="auto")

llama-cpp-python

How to use llmware/bling-answer-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/bling-answer-tool",
	filename="bling-answer.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 llmware/bling-answer-tool with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/bling-answer-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/bling-answer-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/bling-answer-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/bling-answer-tool

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 llmware/bling-answer-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/bling-answer-tool

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 llmware/bling-answer-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/bling-answer-tool

Use Docker

docker model run hf.co/llmware/bling-answer-tool

LM Studio
Jan
Ollama
How to use llmware/bling-answer-tool with Ollama:
```
ollama run hf.co/llmware/bling-answer-tool
```

Unsloth Studio new

How to use llmware/bling-answer-tool 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 llmware/bling-answer-tool 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 llmware/bling-answer-tool to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/bling-answer-tool to start chatting

Docker Model Runner
How to use llmware/bling-answer-tool with Docker Model Runner:
```
docker model run hf.co/llmware/bling-answer-tool
```

Lemonade

How to use llmware/bling-answer-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/bling-answer-tool

Run and chat with the model

lemonade run user.bling-answer-tool-{{QUANT_TAG}}

List all available models

lemonade list

Model Card for Model ID

bling-answer-tool is a quantized version of BLING Tiny-Llama 1B, with 4_K_M GGUF quantization, providing a very fast, very small inference implementation for use on CPUs.

bling-tiny-llama is a fact-based question-answering model, optimized for complex business documents.

To pull the model via API:

from huggingface_hub import snapshot_download           
snapshot_download("llmware/bling-answer-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)

Load in your favorite GGUF inference engine, or try with llmware as follows:

from llmware.models import ModelCatalog  
model = ModelCatalog().load_model("bling-answer-tool")            
response = model.inference(query, add_context=text_sample)

Note: please review config.json in the repository for prompt wrapping information, details on the model, and full test set.

Model Description

Developed by: llmware
Model type: GGUF
Language(s) (NLP): English
License: Apache 2.0
Quantized from model: llmware/bling-tiny-llama

Model Card Contact

Darren Oberst & llmware team

Downloads last month: 130

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Collection including llmware/bling-answer-tool

BLING Models

Collection

Small CPU-based RAG-optimized, instruct-following 1B-3B parameter models • 27 items • Updated Jan 11 • 28