Hebrew-Gemma-11B-V2/README.md

---
license: other
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
language:
- en
- he
library_name: transformers
---
# Hebrew-Gemma-11B-V2

An updated version of [Hebrew-Gemma-11B](https://huggingface.co/yam-peleg/Hebrew-Gemma-11B) that was trained longer and had some bugs fixes.

### Base Models:
- **07.03.2024:** [Hebrew-Gemma-11B](https://huggingface.co/yam-peleg/Hebrew-Gemma-11B)
- **16.03.2024:** [Hebrew-Gemma-11B-V2](https://huggingface.co/yam-peleg/Hebrew-Gemma-11B-V2)

### Instruct Models:
- **07.03.2024:** [Hebrew-Gemma-11B-Instruct](https://huggingface.co/yam-peleg/Hebrew-Gemma-11B-Instruct)

Hebrew-Gemma-11B is an open-source Large Language Model (LLM) is a hebrew/english pretrained generative text model with 11 billion parameters, based on the Gemma-7B architecture from Google.

It is continued pretrain of gemma-7b, extended to a larger scale and trained on 3B additional tokens of both English and Hebrew text data.

The resulting model Gemma-11B is a powerful general-purpose language model suitable for a wide range of natural language processing tasks, with a focus on Hebrew language understanding and generation.


### Terms of Use

As an extention of Gemma-7B, this model is subject to the original license and terms of use by Google.

**Gemma-7B original Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)

### Usage

Below are some code snippets on how to get quickly started with running the model.

First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.

### Running on CPU

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")

input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```

### Running on GPU

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2", device_map="auto")

input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```

### Running with 4-Bit precision

```python
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2", quantization_config = BitsAndBytesConfig(load_in_4bit=True))

input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0])
```

### Benchmark Results

- Coming Soon!


### Notice

Hebrew-Gemma-11B-V2 is a pretrained base model and therefore does not have any moderation mechanisms.


### Authors

- Trained by Yam Peleg.
- In collaboration with Jonathan Rouach and Arjeo, inc.