Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
- he
|
| 7 |
+
tags:
|
| 8 |
+
- pretrained
|
| 9 |
+
inference:
|
| 10 |
+
parameters:
|
| 11 |
+
temperature: 0.6
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
[<img src="https://i.ibb.co/5Lbwyr1/dicta-logo.jpg" width="300px"/>](https://dicta.org.il)
|
| 15 |
+
|
| 16 |
+
# Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs
|
| 17 |
+
|
| 18 |
+
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.
|
| 19 |
+
|
| 20 |
+
This is the 1.7-billion-parameter base model, originally initialized from [Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base).
|
| 21 |
+
|
| 22 |
+
This version of the model is quantized to 4-bits (with 16-bit activations), allowing for inference with significantly less memory although with weaker performance.
|
| 23 |
+
|
| 24 |
+
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).
|
| 25 |
+
|
| 26 |
+
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.
|
| 27 |
+
|
| 28 |
+
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).
|
| 29 |
+
|
| 30 |
+
## Usage
|
| 31 |
+
|
| 32 |
+
### vLLM
|
| 33 |
+
|
| 34 |
+
```bash
|
| 35 |
+
vllm serve dicta-il/DictaLM-3.0-1.7B-Base-W4A16
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
## Notice
|
| 39 |
+
|
| 40 |
+
DictaLM-3.0-1.7B-Base-W4A16 is a pretrained base model and therefore does not have any moderation mechanisms.
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
## Citation
|
| 44 |
+
|
| 45 |
+
If you use this model, please cite:
|
| 46 |
+
|
| 47 |
+
```bibtex
|
| 48 |
+
@article{Shmidman2025DictaLM3,
|
| 49 |
+
title={{Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs}},
|
| 50 |
+
author={Shaltiel Shmidman and Avi Shmidman and Amir DN Cohen and Moshe Koppel},
|
| 51 |
+
year={2025},
|
| 52 |
+
publisher={{DICTA / Jerusalem, Israel}},
|
| 53 |
+
note={https://www.dicta.org.il/publications/DictaLM_3_0___Techincal_Report.pdf}
|
| 54 |
+
}
|
| 55 |
+
```
|