Instructions to use mufeedh28/dictalm2-israeli-law-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mufeedh28/dictalm2-israeli-law-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mufeedh28/dictalm2-israeli-law-GGUF",
	filename="dictalm2-israeli-law.F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mufeedh28/dictalm2-israeli-law-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mufeedh28/dictalm2-israeli-law-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf mufeedh28/dictalm2-israeli-law-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mufeedh28/dictalm2-israeli-law-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf mufeedh28/dictalm2-israeli-law-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 mufeedh28/dictalm2-israeli-law-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf mufeedh28/dictalm2-israeli-law-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 mufeedh28/dictalm2-israeli-law-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mufeedh28/dictalm2-israeli-law-GGUF:F16

Use Docker

docker model run hf.co/mufeedh28/dictalm2-israeli-law-GGUF:F16

LM Studio
Jan

vLLM

How to use mufeedh28/dictalm2-israeli-law-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mufeedh28/dictalm2-israeli-law-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": "mufeedh28/dictalm2-israeli-law-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mufeedh28/dictalm2-israeli-law-GGUF:F16

Ollama
How to use mufeedh28/dictalm2-israeli-law-GGUF with Ollama:
```
ollama run hf.co/mufeedh28/dictalm2-israeli-law-GGUF:F16
```

Unsloth Studio

How to use mufeedh28/dictalm2-israeli-law-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 mufeedh28/dictalm2-israeli-law-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 mufeedh28/dictalm2-israeli-law-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mufeedh28/dictalm2-israeli-law-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mufeedh28/dictalm2-israeli-law-GGUF with Docker Model Runner:
```
docker model run hf.co/mufeedh28/dictalm2-israeli-law-GGUF:F16
```

Lemonade

How to use mufeedh28/dictalm2-israeli-law-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mufeedh28/dictalm2-israeli-law-GGUF:F16

Run and chat with the model

lemonade run user.dictalm2-israeli-law-GGUF-F16

List all available models

lemonade list

DictaLM 2.0 — Israeli Law Chat (GGUF)

Run the Hebrew legal chatbot locally with Ollama

F16 full precision | ~14.5 GB | Requires 16GB+ RAM

Quick Start

ollama run hf.co/mufeedh28/dictalm2-israeli-law-GGUF

Then ask questions in Hebrew:

>>> מהן זכויות השוכר לפי חוק השכירות?
>>> מה קורה אם מעסיק לא משלם פיצויי פיטורים?
>>> האם ניתן לערער על החלטת בית משפט השלום?

About

This is the F16 (full precision) GGUF version of DictaLM 2.0 — Israeli Law Chat, a 7B Hebrew legal chatbot fine-tuned on 140K+ Israeli legal documents and 7,291 Q&A pairs.

For full model details, training data, and usage examples, see the main model card.

File Details

File	Precision	Size	Quality
`dictalm2-israeli-law.F16.gguf`	F16	~14.5 GB	Full precision — no quality loss

Requirements

Ollama installed
16 GB+ RAM (GPU or CPU)

Alternative Usage

With llama.cpp directly

./llama-cli -m dictalm2-israeli-law.F16.gguf -p "[INST] מהן זכויות העובד בפיטורים? [/INST]" -n 512

With llama-cpp-python

from llama_cpp import Llama

llm = Llama(model_path="dictalm2-israeli-law.F16.gguf", n_ctx=2048)
output = llm("[INST] מהן זכויות העובד בפיטורים? [/INST]", max_tokens=512, temperature=0.7)
print(output["choices"][0]["text"])

Disclaimer: This model may produce inaccurate legal information. Do not use as a substitute for professional legal advice.

Made by Mufeed Hammud | Full Model | GitHub

Downloads last month: 12

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

16-bit

Model tree for mufeedh28/dictalm2-israeli-law-GGUF

Base model

dicta-il/dictalm2.0

Adapter

mufeedh28/dictalm2-israeli-law-instruct-merged

Quantized

(1)

this model