Instructions to use decisionslab/Dlab-852-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use decisionslab/Dlab-852-8B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="decisionslab/Dlab-852-8B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("decisionslab/Dlab-852-8B-GGUF")
model = AutoModelForCausalLM.from_pretrained("decisionslab/Dlab-852-8B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use decisionslab/Dlab-852-8B-GGUF with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("decisionslab/Dlab-852-8B-GGUF")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use decisionslab/Dlab-852-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="decisionslab/Dlab-852-8B-GGUF",
	filename="ggml-model-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use decisionslab/Dlab-852-8B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf decisionslab/Dlab-852-8B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf decisionslab/Dlab-852-8B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf decisionslab/Dlab-852-8B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf decisionslab/Dlab-852-8B-GGUF:F16

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 decisionslab/Dlab-852-8B-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf decisionslab/Dlab-852-8B-GGUF:F16

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 decisionslab/Dlab-852-8B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf decisionslab/Dlab-852-8B-GGUF:F16

Use Docker

docker model run hf.co/decisionslab/Dlab-852-8B-GGUF:F16

LM Studio
Jan

vLLM

How to use decisionslab/Dlab-852-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "decisionslab/Dlab-852-8B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decisionslab/Dlab-852-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/decisionslab/Dlab-852-8B-GGUF:F16

SGLang

How to use decisionslab/Dlab-852-8B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "decisionslab/Dlab-852-8B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decisionslab/Dlab-852-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "decisionslab/Dlab-852-8B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decisionslab/Dlab-852-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use decisionslab/Dlab-852-8B-GGUF with Ollama:
```
ollama run hf.co/decisionslab/Dlab-852-8B-GGUF:F16
```

Unsloth Studio new

How to use decisionslab/Dlab-852-8B-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 decisionslab/Dlab-852-8B-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 decisionslab/Dlab-852-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for decisionslab/Dlab-852-8B-GGUF to start chatting

MLX LM

How to use decisionslab/Dlab-852-8B-GGUF with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "decisionslab/Dlab-852-8B-GGUF"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "decisionslab/Dlab-852-8B-GGUF"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "decisionslab/Dlab-852-8B-GGUF",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use decisionslab/Dlab-852-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/decisionslab/Dlab-852-8B-GGUF:F16
```

Lemonade

How to use decisionslab/Dlab-852-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull decisionslab/Dlab-852-8B-GGUF:F16

Run and chat with the model

lemonade run user.Dlab-852-8B-GGUF-F16

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

decisionslab/Dlab-852-8B-GGUF

The Model decisionslab/Dlab-852-8B-GGUF was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Llama-8B using mlx-lm version 0.21.1.

Model Overview

Model Name:decisionslab/Dlab-852-8B-GGUF Base Model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Intended Use: Cultural aligned deep reasoning for Hong Kong
Language(s): Primarily English

Model Description

decisionslab/Dlab-852-8B-GGUF is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B, optimized to align with the cultural and social perspectives relevant to Hong Kong. The model is trained using a dataset that includes World Values Survey data and additional Hong Kong-specific datasets curated by Decisions Lab. The goal of this fine-tuning process is to enhance the model's capability with cultural alignment to Hong Kong for deep thinking, and contextual reasoning.

Intended Use Cases

Policy simulation and decision support in Hong Kong-related contexts.
Deep reasoning tasks involving multi-perspective analysis.
Language and social interaction modeling tailored for Hong Kong users.

Evaluation

The model is currently under evaluation, and CD Eval results will be published in a future update.

License

All content in this repository is proprietary and confidential. The software and any associated documentation files are the exclusive property of Decisions Lab. Unauthorized copying, distribution, modification, or use of this software, via any medium, is strictly prohibited. Access to and use of this software requires explicit permission from Decisions Lab.

Contact

For inquiries, collaborations, or feedback, please contact Decisions Lab via hello@decisionslab.com.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F16

MLX

Hardware compatibility

4-bit

Model tree for decisionslab/Dlab-852-8B-GGUF

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Quantized

(192)

this model