Instructions to use dicta-il/dictalm2.0-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dicta-il/dictalm2.0-instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="dicta-il/dictalm2.0-instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dicta-il/dictalm2.0-instruct-GGUF", dtype="auto")

llama-cpp-python

How to use dicta-il/dictalm2.0-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dicta-il/dictalm2.0-instruct-GGUF",
	filename="dictalm2.0-instruct.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 dicta-il/dictalm2.0-instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dicta-il/dictalm2.0-instruct-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf dicta-il/dictalm2.0-instruct-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dicta-il/dictalm2.0-instruct-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf dicta-il/dictalm2.0-instruct-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 dicta-il/dictalm2.0-instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf dicta-il/dictalm2.0-instruct-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 dicta-il/dictalm2.0-instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dicta-il/dictalm2.0-instruct-GGUF:F16

Use Docker

docker model run hf.co/dicta-il/dictalm2.0-instruct-GGUF:F16

LM Studio
Jan

vLLM

How to use dicta-il/dictalm2.0-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dicta-il/dictalm2.0-instruct-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": "dicta-il/dictalm2.0-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dicta-il/dictalm2.0-instruct-GGUF:F16

SGLang

How to use dicta-il/dictalm2.0-instruct-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 "dicta-il/dictalm2.0-instruct-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": "dicta-il/dictalm2.0-instruct-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 "dicta-il/dictalm2.0-instruct-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": "dicta-il/dictalm2.0-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dicta-il/dictalm2.0-instruct-GGUF with Ollama:
```
ollama run hf.co/dicta-il/dictalm2.0-instruct-GGUF:F16
```

Unsloth Studio

How to use dicta-il/dictalm2.0-instruct-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 dicta-il/dictalm2.0-instruct-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 dicta-il/dictalm2.0-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dicta-il/dictalm2.0-instruct-GGUF to start chatting

Docker Model Runner
How to use dicta-il/dictalm2.0-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/dicta-il/dictalm2.0-instruct-GGUF:F16
```

Lemonade

How to use dicta-il/dictalm2.0-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dicta-il/dictalm2.0-instruct-GGUF:F16

Run and chat with the model

lemonade run user.dictalm2.0-instruct-GGUF-F16

List all available models

lemonade list

Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities

The DictaLM-2.0-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the DictaLM-2.0 generative model using a variety of conversation datasets.

For full details of this model please read our release blog post or the technical report.

This is the instruct-tuned model designed for chat in the GGUF format for use with LM Studio or llama.cpp. You can try the model out on a live demo here.

There are two versions available - float16 precision (*.F16.gguf) and 4-bit quantized precision (*.Q4_K_M.gguf).

You can view and access the full collection of base/instruct unquantized/quantized versions of DictaLM-2.0 here.

Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens followed by a line break. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.

E.g.

text = """<s>[INST] איזה רוטב אהוב עליך? [/INST]
טוב, אני די מחבב כמה טיפות מיץ לימון סחוט טרי. זה מוסיף בדיוק את הכמות הנכונה של טעם חמצמץ לכל מה שאני מבשל במטבח!</s>[INST] האם יש לך מתכונים למיונז? [/INST]"

This format is available as a chat template via the apply_chat_template() method:

Using with LM Studio

When using with LM Studio, just search the hub for "dictalm2.0-instruct-GGUF", and the model in both precisions should appear.

Make sure to set the chat template correctly - initialize from the mistral-instruct template, and add a \n in the suffix box, like here:

In addition, the model doesn't support any system prompt, so make sure to remove the system prompt as well.

Model Architecture

DictaLM-2.0-Instruct follows the Zephyr-7B-beta recipe for fine-tuning an instruct model, with an extended instruct dataset for Hebrew.

Limitations

The DictaLM 2.0 Instruct model is a demonstration that the base model can be fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.

Citation

If you use this model, please cite:

@misc{shmidman2024adaptingllmshebrewunveiling,
      title={Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities}, 
      author={Shaltiel Shmidman and Avi Shmidman and Amir DN Cohen and Moshe Koppel},
      year={2024},
      eprint={2407.07080},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.07080}, 
}