Instructions to use razielAI/Duchifat-2.2-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use razielAI/Duchifat-2.2-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="razielAI/Duchifat-2.2-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("razielAI/Duchifat-2.2-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use razielAI/Duchifat-2.2-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "razielAI/Duchifat-2.2-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "razielAI/Duchifat-2.2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/razielAI/Duchifat-2.2-Instruct

SGLang

How to use razielAI/Duchifat-2.2-Instruct 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 "razielAI/Duchifat-2.2-Instruct" \
    --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": "razielAI/Duchifat-2.2-Instruct",
		"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 "razielAI/Duchifat-2.2-Instruct" \
        --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": "razielAI/Duchifat-2.2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use razielAI/Duchifat-2.2-Instruct with Docker Model Runner:
```
docker model run hf.co/razielAI/Duchifat-2.2-Instruct
```

🕊️ Duchifat-2.2-Instruct

Duchifat-2.2-Instruct is a fine-tuned version of the original Duchifat-2 base model. While this specific version is an optimized Instruct/Chat model, the underlying base architecture and weights were developed and trained from scratch by Raziel.

🚀 Lineage & Development

Base Model (Duchifat-2): Built and pre-trained from scratch on 3.27 Billion tokens (50/50 Hebrew-English C4 dataset). It features 136M parameters and was designed to establish a native Hebrew reasoning foundation.
Version 2.2 (Instruct): A refined fine-tuned version (SFT) designed to transform the base capabilities into a quirky, safe, and highly responsive conversational agent.

Key Features:

Native Hebrew Foundation: Unlike models that adapt English weights, Duchifat was born in Hebrew using the DictaLM tokenizer, ensuring high efficiency and natural linguistic flow.
Compact Power: At only 136M parameters, it delivers impressive performance while remaining small enough for edge deployment and low-latency applications.
Quirky & Human-like: The SFT process focused on giving the model a distinct personality—witty and engaging rather than robotic.
Safety Integrated: Built-in guardrails ensure the model remains professional and refuses to engage with profanity or offensive prompts.

📊 Benchmark Results (Zero-Shot)

Tested using manual prompt formatting to accurately reflect real-world chat performance.

Task	Version	Filter	Metric	Value	Stderr
piqa	1	none	acc	0.70	± 0.1528
piqa	1	none	acc_norm	0.70	± 0.1528
hellaswag	1	none	acc	0.40	± 0.1633
hellaswag	1	none	acc_norm	0.40	± 0.1633
winogrande	1	none	acc	0.40	± 0.1633
arc_easy	1	none	acc	0.10	± 0.1000
arc_easy	1	none	acc_norm	0.10	± 0.1000

🛠️ Technical Specifications

Parameters: 136M
Base Pre-training Data: 3.27B tokens (C4 Hebrew/English)
Tokenizer: DictaLM (Hebrew optimized)
Context Window: 1024 tokens

💡 How to Use

Use the following instruction format to trigger the Instruct-tuned behavior:

Prompt Template:

<|instruction|>
{user_query}
<|assistant|>

Example Usage:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "razielAI/Duchifat-2.2-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).to("cuda")

prompt = "<|instruction|>\nשלום!\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

output = model.generate(**inputs, max_new_tokens=256, temperature=0.7, do_sample=True)
print(tokenizer.decode(output[0], skip_special_tokens=True))

⚠️ Limitations

Duchifat-2.2 is a lightweight model. It excels at conversational tasks, social media content, and short-form text generation. It is not designed for complex mathematical proofs or extensive coding sessions.

🕊️ About the Duchifat Project

The Duchifat (Hoopoe) project is dedicated to creating efficient, open-source AI with a native understanding of the Hebrew language and culture.

Downloads last month: 63

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for razielAI/Duchifat-2.2-Instruct

Base model

Raziel1234/Duchifat-2

Finetuned

(8)

this model