---
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 24-billion-parameter base model, with full precision (BF16), originally initialized from [Mistral-Small-3.1-24B-Base-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503).

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).

Note: This is not a chat model; rather this is a base model that can be further fine-tuned. Chat model variants are available at the link below.

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).

## Usage


### Transformers

```python
from transformers import pipeline
import torch

# This loads the model onto the GPU in bfloat16 precision
model = pipeline('text-generation', 'dicta-il/DictaLM-3.0-24B-Base', torch_dtype=torch.bfloat16, device_map='auto')

# Sample few shot examples
prompt = """
עבר: הלכתי
עתיד: אלך

עבר: שמרתי
עתיד: אשמור

עבר: שמעתי
עתיד: אשמע

עבר: הבנתי
עתיד:
"""

print(model(prompt.strip(), do_sample=False, max_new_tokens=8, stop_sequence='\n'))
# [{'generated_text': 'עבר: הלכתי\nעתיד: אלך\n\nעבר: שמרתי\nעתיד: אשמור\n\nעבר: שמעתי\nעתיד: אשמע\n\nעבר: הבנתי\nעתיד: אבין\n\nעבר: קרא'}]
```

### vLLM

```bash
vllm serve dicta-il/DictaLM-3.0-24B-Base 
```

> If you run out of memory, you can try limiting the context window by setting `--max-model-len 8192`


## Notice

DictaLM-3.0-24-Base is a pretrained base model and therefore does not have any moderation mechanisms.


## 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}
}
```