96 lines
4.5 KiB
Markdown
96 lines
4.5 KiB
Markdown
|
---
|
|||
|
|
license: apache-2.0
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
- he
|
|||
|
|
tags:
|
|||
|
|
- pretrained
|
|||
|
|
inference:
|
|||
|
|
parameters:
|
|||
|
|
temperature: 0.6
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
[<img src="https://i.ibb.co/5Lbwyr1/dicta-logo.jpg" width="300px"/>](https://dicta.org.il)
|
|||
|
|
|
|||
|
|
# Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs
|
|||
|
|
|
|||
|
|
Dicta-LM 3.0 is a powerful open-weight collection of LLMs, trained on extensive corpora of Hebrew and English texts. The models are available for download and for unlimited use. The models set a new SOTA for their weight-class for Hebrew, both as base models and chat models.
|
|||
|
|
|
|||
|
|
This is the 1.7-billion-parameter *reasoning* model, with full precision (BF16), originally initialized from [Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base).
|
|||
|
|
|
|||
|
|
This model is a reasoning chat model, which means that before responding to any given message from the user, the model first thinks out the right way to respond in a designated thinking block.
|
|||
|
|
|
|||
|
|
For full details of this model please read our [release blog post](https://dicta.org.il/dicta-lm-3) or the [technical report](https://www.dicta.org.il/publications/DictaLM_3_0___Techincal_Report.pdf).
|
|||
|
|
|
|||
|
|
You can view and access the full collection of base/instruct unquantized/quantized versions of `DictaLM 3.0` [here](https://huggingface.co/collections/dicta-il/dictalm-30-collection).
|
|||
|
|
|
|||
|
|
## Instruction format
|
|||
|
|
|
|||
|
|
In order to leverage instruction fine-tuning, your prompt should be rendered using the chat template specified for this model. Most libraries deal with this automatically, so you can just let them do it.
|
|||
|
|
|
|||
|
|
## Usage
|
|||
|
|
|
|||
|
|
We recommend using vLLM, but you can use Transformers as well:
|
|||
|
|
|
|||
|
|
### Transformers
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
|
|||
|
|
from transformers import pipeline
|
|||
|
|
|
|||
|
|
generator = pipeline('text-generation', model="dicta-il/DictaLM-3.0-1.7B-Thinking")
|
|||
|
|
|
|||
|
|
messages = [
|
|||
|
|
{"role": "user", "content": "איזה רוטב אהוב עליך?"},
|
|||
|
|
{"role": "assistant", "content": "טוב, אני די מחבב כמה טיפות מיץ לימון סחוט טרי. זה מוסיף בדיוק את הכמות הנכונה של טעם חמצמץ לכל מה שאני מבשל במטבח!"},
|
|||
|
|
{"role": "user", "content": "האם יש לך מתכונים למיונז?"}
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
print(generator(messages)[0]['generated_text'][-1]) # just print the last message
|
|||
|
|
# 'role': 'assistant', 'content': 'המשתמש שואל: "האם יש לך מתכונים למיונז?" אנחנו צריכים לספק מתכונים למיונז. לספק מתכונים ברורים, אולי עם שלבים. לספק כמה גרסאות. צריך להיות ידידותי.</think>בהחלט! הנה כמה מתכונים קלים, טעימים למיונז שתוכל לנסות. בחר את זה שמתאים לאפיון המטבח שלך, והרגיש חופשי להתאים את העוצמה של החריפות או התיבול לפי הטעם שלך.\n\n---\n\n## 1. מיונז בסיסי (מתכון בסיסי)\n\n**מרכיבים**\n- 2 כוסות חלב (או כל חלב מתוק אחר)\n- 1 ביצה גדולה\n- 1 כפית מיץ לימון טרי\n- 1 כפית מיץ תפוזים טרי (אופציונלי)\n- 1⁄2 כפית חרדל דיז\'ון\n- 1⁄2 כפית מלח\n- 1⁄4 כפית פלפל שחור טחון טרי\n\n**הוראות**\n1. **הכנת הביצה** – בקערה, טורפים יחד ביצה'}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### vLLM
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
vllm serve dicta-il/DictaLM-3.0-1.7B-Thinking --enable-auto-tool-choice --tool-call-parser hermes --reasoning_parser deepseek_r1
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
And then you can access it via the openai library:
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from openai import OpenAI
|
|||
|
|
|
|||
|
|
client = OpenAI(
|
|||
|
|
base_url="http://localhost:8000/v1",
|
|||
|
|
api_key="sk-no-key-required"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
response = client.chat.completions.create(
|
|||
|
|
model="dicta-il/DictaLM-3.0-1.7B-Thinking",
|
|||
|
|
messages=[
|
|||
|
|
{"role": "user", "content": "Hello, how are you?"}
|
|||
|
|
],
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print(response.choices[0].message.content)
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
> The reasoning traces should be available in the response structure in the designated fild.
|
|||
|
|
|
|||
|
|
The model supports tool-calling, enabling integration with external tools and APIs. For example how to use the tool calling, see the [vLLM documentation](https://docs.vllm.ai/en/stable/features/tool_calling/#tool-calling).
|
|||
|
|
|
|||
|
|
## Citation
|
|||
|
|
|
|||
|
|
If you use this model, please cite:
|
|||
|
|
|
|||
|
|
```bibtex
|
|||
|
|
@article{Shmidman2025DictaLM3,
|
|||
|
|
title={{Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs}},
|
|||
|
|
author={Shaltiel Shmidman and Avi Shmidman and Amir DN Cohen and Moshe Koppel},
|
|||
|
|
year={2025},
|
|||
|
|
publisher={{DICTA / Jerusalem, Israel}},
|
|||
|
|
note={https://www.dicta.org.il/publications/DictaLM_3_0___Techincal_Report.pdf}
|
|||
|
|
}
|
|||
|
|
```
|